Data science, intelligence and future analysis
Mohammad Amin Yalpanian; Iman Raeesi Vanani; Mohammad Taghi Taghavifard
Abstract
The ever-increasing development of digital technologies has brought about significant changes in business performance. The increase in the number of published articles on this topic also shows the special attention of researchers in information systems, business management, and innovation. While digital ...
Read More
The ever-increasing development of digital technologies has brought about significant changes in business performance. The increase in the number of published articles on this topic also shows the special attention of researchers in information systems, business management, and innovation. While digital changes are inevitable in the digital age, previous research has been limited to a specific domain. This research aims to identify key themes and macro topics through a systematic review of 201 articles from 2018 to 2023 through two high-quality databases (Scopus and Web of Science). First, using thematic analysis, the main themes are identified, and their relationships are investigated from the perspective of digital technology development. In the next step, by using topic modeling (Latent Dirichlet Allocation), the major domains of the impact of these technologies will be investigated, and future research trends will be identified using the scientometric approach. The innovation of this research is designing a thematic network through in-depth text review and text mining analysis, which leads to a better understanding of the relationships between critical components. In the last step, recommendations are given to researchers and managers to conduct future research.
Data science, intelligence and future analysis
Manijeh Ramsheh; mohammad hasan maleki; narges sarlak; monireh falahat bangdeh
Abstract
Fintech and its entrepreneurial opportunities have the ability to play an effective role in the development of the financial industry. Therefore, it is necessary to make a correct and effective policy in this area to identify its probable future. This study is exploratory in terms of purpose and practical ...
Read More
Fintech and its entrepreneurial opportunities have the ability to play an effective role in the development of the financial industry. Therefore, it is necessary to make a correct and effective policy in this area to identify its probable future. This study is exploratory in terms of purpose and practical in terms of orientation. Interviews and questionnaires were used to collect data. 28 drivers were extracted by reviewing the background and interviewing experts. In order to screen the propellants, expert questionnaire and fuzzy Delphi method were used. Then the propellants screened were ranked through the priority assessment questionnaire and the developed COPRAS technique. The two drivers of the development of smart contracts in the financial industry and the tendency of financial institutions towards open innovation had the highest priority and were used to write research scenarios. Based on these two drivers, 4 scenarios of the era of pristine opportunities, the era of conservative managers, the era of dilapidated infrastructure and the ice age were developed. Then, using the MABAC technique, the scenario of the age of dilapidated infrastructures was selected as the possible scenario of the research. Research proposals were proposed based on priority drivers and possible scenarios. Government support, providing sufficient funds in order to create the necessary infrastructure for the development of smart contracts by banks or establishing a cooperative relationship between banks and financial institutions, fair legislation, development of regtechs, creating compatibility between current systems with new technologies were the most important practical proposals of the study.IntroductionThe financial industry includes a set of institutions and organizations that allocate credit and equip resources. The development of economic activities requires investment, and investment also requires the provision of financial resources, which is an important task for the financial industry. Therefore, the development of the financial industry is the driver of economic development. Therefore, the increasing need for new technologies to improve performance and increase efficiency in the financial industry is strongly felt. One of the working models affecting the financial industry is fintech (Qaemi & et al., 2017). Fintech is a field that uses innovative technologies to provide all services of the financial industry with greater speed and transparency and lower cost while maintaining security and quality (Zavolokina et al., 2016). According to reports, global fintech investments have grown from $9 billion in 2010 to $25 billion in 2016. Fintech's market share this year was not even 1%, but it is expected to increase to 35% by 2023 (Koshesh Kordsholi & et al., 2021). In Iran, one of the priorities of the sixth development plan is the issue of financing and expansion of financial instruments, which the financial and banking actors have encouraged to support fintech startups in order to realize innovation and expand their services (Qaemi & et al., 2017). But the fact is that fintech in Iran is behind the rest of the world. In iran, due to several problems, including legal challenges, technology problems, financing, etc., fintech businesses are not growing and there are many entrepreneurial opportunities in this field that have not been addressed. Thus, the current research seeks to answer the following questions:What are the key drivers affecting the future of fintech entrepreneurial opportunities in Iran?What is the degree of priority of the key drivers affecting the future of fintech entrepreneurial opportunities in Iran?What are the plausible future scenarios of fintech entrepreneurial opportunities in Iran?What is the possible future scenario of fintech entrepreneurial opportunities in Iran?Literature ReviewFintech can be considered as any innovative idea that improves financial services processes by providing technological solutions according to different business situations) Suryono & et al., 2020). Fintech startups are looking for new approaches to business models, improving customer experience and new approaches that lead to service changes and are trying to enter financial systems and challenge traditional financial institutions (Gomber et al., 2018). If the context and the possibility of growth and application of entrepreneurial opportunities hidden in the field of fintech, which are in their maturity stage, are provided; It will follow the increasing economic progress of the countries.Uncertainty about the future of organizations prompts managers to look for new tools and methods to determine future situations and create the future. Future research is a systematic way to look at the long-term future in any field and draw it, the main purpose of which is to know the new structures, mechanisms, opportunities and processes and to determine the sectors that have more efficiency. Understanding and applying futurist theories and methods enables individuals and groups to more usefully anticipate the future and shape it to a greater extent based on their preferences (Dator et al., 2019).MethodologyIn this research, four quantitative methods, fuzzy Delphi, entropy, developed COPRAS and MABAC technique were used. Also, to develop believable research scenarios, the qualitative method of the consultation workshop was used. The theoretical community of this research is 10 members of the academic staff of the university, fintech experts, managers of fintech businesses, experts of fintech associations and senior experts of the central bank in the regulatory field. The sampling method of the present study is judgmental and based on the expertise of individuals in the field of fintech. The steps of the current research are: 1) background review and interviews with experts to identify drivers affecting the future of fintech entrepreneurial opportunities in Iran; 2) Screening research drivers with the fuzzy Delphi technique; 3) prioritizing the final drives with the developed COPRAS method; 4) Compilation of plausible future scenarios of Iran's fintech entrepreneurship opportunities using a consultation workshop (participation of 7 experts); 5) Selecting a possible research scenario using the MABAC technique.ResultsAt first, 28 drivers were extracted through reviewing financial technology-oriented backgrounds and interviewing experts. Then, with the application of expert questionnaire and fuzzy Delphi technique, 15 drivers were removed from the calculations and 13 drivers were selected to extract the effect model of drivers. Based on the output of COPRAS technique, the drivers for the development of smart contracts in the financial industry are the tendency of financial institutions towards open innovation, the variety of financing methods and the attitude of the regulator towards fintechs, respectively, they have the most importance in terms of influencing the future of fintech entrepreneurial opportunities. The two drivers of smart contract development and the trend of financial institutions towards open innovation were used to map research scenarios. Considering that for each driver, two opposite situations can be set, four scenarios were developed, which are: the era of pristine opportunities, the era of conservative managers, the era of dilapidated infrastructure, and the ice age. In the following, MABAC technique was used to select the possible research scenario. The ranking of the research scenarios in terms of 3 selected indicators is such that the scenario of the age of dilapidated infrastructures is the most likely research scenario. The ice age scenarios, the conservative managers era scenario, and the pristine opportunities era scenario were ranked next.ConclusionThe trend of financial institutions towards open innovation in the scenario of the age of worn out infrastructure shows that the development of digital technologies has gradually created interest in the managers of this industry and has improved their attitude towards themselves. But the lack of development of smart contracts in the financial industry in this future has several reasons. Among the reasons for this lack of development, we can mention the lack of necessary infrastructure for the development of information technology, which is mainly due to the lack of support from the government and the relevant ministry and their lack of attention to the importance of learning information technology. In addition, banks should also provide the necessary funds in order to create the necessary infrastructure for the development of smart contracts, and if there is a heavy cost, establish a cooperative relationship between the banks and financial institutions of the country along with government support to reduce the cost and implement it in a tangible way. Another important discussion in this field is that fair regulation is necessary for the spread of smart contracts. Strengthening regtechs through science and technology parks and growth centers can also help. Another important reason for not developing smart contracts is the incompatibility of current systems with new technologies, which prompts managers of financial institutions to change the system and make them compatible. Lack of sufficient training for financial industry activists can also be another factor for this lack of development.Keywords: Future Study, Driver, Scenario Planning, Entrepreneurial Opportunities, Fintech
Data science, intelligence and future analysis
Fariba Karimi; ameneh khadivar; Fatemeh Abbasi
Abstract
In recent years, the rapid growth of virtual space has made people devote more of their time in virtual space, especially to social networks, which can be attributed to the remarkable features of virtual space; including increasing the speed of information exchange, easy and free access to information ...
Read More
In recent years, the rapid growth of virtual space has made people devote more of their time in virtual space, especially to social networks, which can be attributed to the remarkable features of virtual space; including increasing the speed of information exchange, easy and free access to information and variety of knowledge topics. In this regard, the opinions recorded by users in virtual networks have grown day by day and have become very important, and extracting the opinions and feelings of users' opinions for more informed decision-making is of great help to businesses, on the other hand, virtual reality technology in the past few decades It has undergone technical changes and improved immersion and the feeling of remote presence; This technology is used in various fields such as education, tourism, health, sports, entertainment, architecture and construction, etc. The increasing progress of virtual reality technology has caused many businesses to operate in this field, but due to changes Continuous market and the need for timely information, companies should use differentiation and growth strategies, in this regard, they need to ask users' opinions and in line with that, try to grow and improve their business, considering that Users' comments are textual, and reading and summarizing them is time-consuming and difficult. Based on this, the aim of the current research was to categorize comments related to virtual reality technology using machine learning methods and a dictionary-based approach. Therefore, about one million tweets in the field of virtual reality technology were collected by the web crawler, and after data preprocessing, 480,432 samples remained in the data, then Dirichlet's hidden allocation topic modeling was implemented on the data. This modeling separated different topics by examining the distribution of words in tweets; The tweets whose distribution of words were similar were placed into a topic and the number of topics with the highest coherence score was selected, the number of topics 9 had higher coherence and the data were grouped into 9 topics, so once again the Dirichlet hidden allocation modeling was set to 9. The topic was done, with this the tweets were grouped into 9 different topics. To evaluate the model, considering that we had a probability distribution, the confusion criterion was used, the value of which was -9.44, and the coherence score was used for the degree of semantic similarity between words and the distinction between subjects, and the result was 0.47. The lower the confusion criterion and the higher the coherence score, the more efficient the model is. With the help of keyword weights obtained by Dirichlet hidden allocation modeling and examining at least 5 different tweets from each topic, 9 topics related to virtual reality technology were identified: "New Technology", "Creation and Make", "Technological Business", "Education", "Virtual Games", "Progress", "Gadget", "Metaverse", and "Indiegame", the topics were analyzed with the help of several graphs. We found that the number of neutral comments on topics such as "New Technology" and "Metaverse" is more than positive and negative comments, which indicates the lack of sufficient information or the lack of use of these technologies, and it is necessary for businesses in this field, to try more in this regard, in the same way, if we observe the graph of "Virtual Games" and "Technological Business", we can see that it changes almost with the same ratio in different years, in the sense that this The two graphs are related, in fact, businesses should keep in mind that the factors affecting these two issues are the same, but users pay more attention to the issue of "Virtual Games", as a result, if the creators of "Technological Business" Focus specifically on "Virtual Games", they will grow more due to the more attention of users, also the creators of games should consider that "Virtual Games" are a topic of more attention than "Indiegame". Is. In the subjects of "Education" and "Gadget", users lost their attention to these subjects in the field of virtual reality over time, in fact they showed their attention to other subjects, so it is better for businesses that operate in this field to take measures To advertise and attract users or change their user area if there is no growth.
Introduction
Constant changes in the market and the need for timely information force companies to use differentiation and growth strategies appropriate to the needs of customers. (Sánchez, Folgado-Fernández, & Sánchez, 2022). Companies can check and analyze their customers' opinions through microblogging sites (Facebook, Twitter, etc.) and finally improve the desired products or services (Ahmad, Aftab, Bashir, & Hameed, 2018). Today, users express their opinions and feelings and review products in online social networks. Therefore, user comments and the analysis of these comments have become a valuable resource for businesses (Kim et al., 2015; Loureiro et al., 2019).
Virtual reality and augmented reality have undergone technical developments in the past few decades and have improved immersion and the feeling of remote presence. Several examples of applications of such techniques can be found in stores, the tourism industry, hotels, restaurants, etc. (Loureiro, Guerreiro, & Ali, 2020). Due to the constant changes in the market and the need for timely information, companies should use differentiation and growth strategies, nowadays, due to the rapid evolution of the Internet, instead of collecting their opinions through time-consuming and expensive methods such as questionnaires and interviews, etc., they express in the context of social networks, which is very useful for businesses in their development, and they can measure the feelings of customers towards products and services, and understand the needs of users, and finally make appropriate and appropriate decisions in the direction of adopt growth, but in order to use the produced content correctly, text mining and sentiment analysis techniques should be used, which has not been researched in Iran so far. Analysis of users' opinions and feelings about virtual reality technology can help businesses that operate in the field of metaverse, virtual game production, virtual education, virtual tourism, etc., to make better decisions and plans.
Literature Review
Social media generates a large amount of real-time social signals that can provide new insights into human behavior and emotions. People around the world are constantly engaged with social media. (Al-Samarraie, Sarsam, & Alzahrani, 2023).
On the other hand, the amount of data is increasing day by day. Almost all institutions, organizations and business industries store their data electronically. A huge amount of text is circulating on the Internet in the form of digital libraries, repositories, and other textual information such as blogs, social media networks, and emails (Sagayam, Srinivasan, & Roshni, 2012).
Topic modeling is one of the most powerful techniques in text mining for data mining, discovering hidden data and finding relationships between data and textual documents (Jelodar et al., 2017).
The technological advances of the last century have confronted societies with new realities that have indisputably improved daily life, making it more convenient and interesting. In recent decades, technology using virtual reality and wearable devices have had a significant impact in the fields of education, tourism, health, sports, entertainment, architecture and construction, etc. (Kosti et al., 2023).
Virtual reality is a technology that allows a user to interact with a computer-simulated environment, whether that environment is a simulation of the real world or an imaginary one. With virtual reality, we can experience the most frightening and overwhelming situations with safe play and a learning perspective (Mandal, 2013). Most people are curious about the possibilities and future of new technologies, considering the various applications it is supposed to offer such as virtual meetings, learning environments and many others, however, there are also concerns about potential negative effects. because real world signals can be transmitted in the virtual world. In this regard, people express their feelings in different social networks (Bhattacharyya et al., 2023).
Methodology
According to the main goal of the research, which is to classify comments related to virtual reality technology using machine learning methods and a dictionary-based approach, therefore, about one million tweets in the field of virtual reality technology were collected by the web crawler and After data preprocessing, 480,432 samples remained in the data, then Dirichlet hidden allocation thematic modeling was implemented on the data. By examining the distribution of words in tweets, this modeling tries to separate different topics by detecting the distribution of words; The tweets whose distribution of words are similar were put into a topic, and the number of topics with the highest score was selected, the number of topics 9 has higher coherence, and the data was grouped into 9 topics, so once again, Dirichlet hidden allocation modeling was applied 9 topics were done, whereby the tweets were grouped into 9 different topics. Considering that we have a probability distribution, the confusion criterion was used to evaluate the model. The lower the confusion criterion and the higher the coherence score, the more efficient the model is. With the help of keyword weights obtained by Dirichlet hidden allocation modeling and examining at least 5 different tweets from each topic, 9 topics related to virtual reality technology were identified: "New Technologies", "Creation and Make", "Technological Business", "Education", "Virtual Games", "Progress", "Gadget", "Metaverse" and "Indiegame" were named.
Discussion and Conclusion
In this research, by examining topics in different years, we observed that the topic of "Progress" was the most popular topic among users from 2017 to the end of 2021, in early 2022, this topic gave way to "Metaverse", currently "Metaverse" is one of the most popular topics being discussed by users. Businesses in the field of virtual reality should strive for the attractiveness of "Metaverse" and attract users. Likewise, if we observe the "Virtual Games" and "Technological Business" graphs, we can see that they change with almost the same ratio in different years, meaning that these graphs are related to each other, in fact, business and keep in mind that the factors affecting these two issues are the same, but in the case of "Virtual Games" it has more effects, and if "Technological Businesses" specifically focus on virtual games, they will grow more due to the greater attention of users. had Similarly, "Indiegame" which have had a series of changes but in recent years have had a declining trend and then no change, now the creators of these games should check, and in general "Virtual Games" are a more interesting topic than "Indiegame". In the subjects of "Education" and "Gadget" it has been decreasing since the beginning of 2017, which shows that users lost their attention to these subjects in the field of virtual reality over time, in fact to other topics showed their attention, so it is better for businesses that are active in this field to take measures to advertise and attract users, or change their user field if there is no growth.
Keywords: Data Mining, Text Mining, Virtual Reality Technology, Topic Modeling, Latent Dirichlet Allocation.
Data science, intelligence and future analysis
Seyed Mohammad Mahmoudi; Mohammad Jafari; mahsa Pishdar
Abstract
Artificial intelligence provides unique opportunities to improve the performance of various industries, including the automotive industry. The present study seeks to identify the applications and requirements of using artificial intelligence in new automotive products such as self-driving cars ...
Read More
Artificial intelligence provides unique opportunities to improve the performance of various industries, including the automotive industry. The present study seeks to identify the applications and requirements of using artificial intelligence in new automotive products such as self-driving cars by obtaining opinions from managers and employees of domestic automotive companies through semi-structured interviews and thematic analysis. The interviewees included 11 managers and 17 employees, of which 15 had a bachelor's degree, 11 had a master's degree, and 2 had a doctorate degree. 21 codes were identified in the applications section and 26 codes were identified in the requirements section. After conducting 28 interviews, theoretical saturation was achieved. From the codes identified in the applications section, self-driving cars and voice assistants, shared transportation, and resource allocation, expert staff, and team formation can be mentioned in the requirements section. Considering the variety of artificial intelligence applications in new car products and according to the specified requirements according to the opinions of experts, the development of a suitable platform for hard and soft technologies in an integrated manner; And government support regarding the creation of legal infrastructure can improve the development path of the current technology. Of course, in order to create a context for the successful operation of artificial intelligence in the automotive industry, all the effects of its application from different cultural and social aspects should be considered with a systematic perspective.
Introduction
Artificial intelligence has enormous potential to reduce the problems of automakers around the world. Nevertheless, reports show that between 2017 and 2019, the number of automobile manufacturers that consciously refrained from using artificial intelligence and related technologies such as machine learning and neural networks in the production and supply of new products such as connected and autonomous cars have done so; it has only increased from 26% to 39% (Gandhi et al., 2022).
The lack of attention to the complexities of artificial intelligence and the acceleration of the use of this technological tool have caused the failure of automobile manufacturers' plans to provide intelligent products (Fernandes et al., 2022). Despite the applications and benefits of artificial intelligence in automotive services, there are still many ambiguous aspects regarding the use cases and prerequisites that different researches have addressed from a specific perspective, and the lack of a framework consistency in this area is felt. For example, Gupta and colleagues (2021) argue in their research that cars equipped with artificial intelligence technology are not capable of evaluating and classifying their environment on their own.
The present study aims to identify applications and requirements related to the use of artificial intelligence in new automotive products, such as self-driving cars. Therefore, the results of this study can be useful to automobile manufacturers trying to revitalize the potential and improve their products in the field of using artificial intelligence.
Research Question(s)
In this regard, in order to achieve the objectives of the research, a fundamental question is posed:
“What are the requirements and prerequisites for using artificial intelligence in the delivery of new products such as autonomous and connected cars"?
Literature Review
The applications of artificial intelligence in automotive products can be divided into two categories: personal applications and social applications. Personal applications refer to products designed with two elements of security and convenience for users in mind. These applications include cruise control, automatic parking, voice assistant, alert systems, and route suggestion systems, all of which manifest in self-driving cars (Paliotto et al., 2022). Social applications refer to products whose effects include all members of society. For example, self-driving cars and cars equipped with artificial intelligence will reduce urban congestion or reduce the need for parking. These cars also play an effective role in transporting disabled and vulnerable people. Other social applications include the role of these cars in reducing environmental pollution and shared transportation (Zhang et al).
Regarding the requirements and prerequisites for the use of artificial intelligence in modern automotive products, various researches have been carried out, among which we will cite only a few examples below:
- Barzegar and Elham (2019), using a descriptive-analytical approach, the criminal liability of the user of self-driving cars in accidents was discussed.
- Demlehner et al. (2021) conducted a study to identify 20 applications of artificial intelligence in the production of intelligent and autonomous cars and to examine these applications from the two dimensions of business value and realizability.
- Othman (2022) studied the requirements for the use of artificial intelligence in automotive products, such as cruise control, warning systems and self-driving cars, and studied its consequences from the point of view security, the economy and society, etc.
Methodology
This research is”an applied research”in terms of purpose and a descriptive survey in terms of data collection. The information collection method is a survey and semi-structured interview with experts. The experts include two categories of managers and senior employees from the research and development department of interior automakers who have more than five years of work experience and are familiar with artificial intelligence. In order to collect samples, semi-structured interviews were conducted with the target people in person or in person using the snowball method.
The method of data analysis in this research is thematic analysis; so, after implementing the text of the interviews and analyzing and coding it with the thematic analysis method, 21 codes were identified in the applications section and 26 codes were identified in the requirements section. After carrying out 28 interviews, theoretical saturation was reached. From the codes identified in the applications section we can refer to self-driving cars, voice assistant, and in the requirements section we can refer to resource allocation, specialized personnel.
Results
The main goal of this research was to identify the applications and requirements related to the use of artificial intelligence in new car products, such as self-driving cars. According to the review and analysis of the interviews with the thematic analysis method, the research results were determined into two groups:
In the first group, applications of artificial intelligence in new products of automobile manufacturers were identified, such as self-driving cars, cruise control and warning systems, among which, according to the interviews, self-driving cars were the most important. Therefore, in this research, emphasis was placed on identifying key applications, which were separated into two dimensions: personal and social applications; In this regard, a total of 21 applications were identified.
In the second group, the requirements and prerequisites of artificial intelligence were classified, and due to the dispersion of results in previous research, a great effort was made to integrate the requirements. In this regard, the requirements of artificial intelligence are divided into six general categories, which are: 1- road infrastructure, 2- technical infrastructure and equipment, 3- knowledge, 4- users, 5- the role of managers, 6- culture, Rules. Therefore, as far as possible, in this category, fundamental requirements such as society, individual, technology and knowledge have been taken into account.
In short, taking into account the diversity of applications of artificial intelligence in modern automotive products, it can be concluded that, according to the established requirements and opinions of experts, the development of a suitable and integrated platform of hard technologies and soft law requires serious support from the government and attention to the creation of legal infrastructure. Therefore, we suggest that policy makers and managers of the automobile industry, in order to facilitate the technological development and optimal use, and successful application of artificial intelligence in the automobile industry, should all first systematize their point of view, and pay particular attention to the necessary infrastructure and consider different dimensions such as technical, cultural, social, etc.
Keywords: Artificial intelligence, applications and requirements, new products, self-driving cars..
Data science, intelligence and future analysis
Mohammad Hasan Maleki; Seyed Morteza Mortazavi; Shahriar Shirooyehpour; Mohammad Javad Zare Bahnamiri
Abstract
AbstractThis research has been done with the aim of developing Iran's banking scenarios with an emphasis on big data. The current research is practical in terms of orientation and exploratory in terms of the goal. It is also mixed in terms of its philosophical, pragmatic and methodological foundations. ...
Read More
AbstractThis research has been done with the aim of developing Iran's banking scenarios with an emphasis on big data. The current research is practical in terms of orientation and exploratory in terms of the goal. It is also mixed in terms of its philosophical, pragmatic and methodological foundations. To carry out the research in the first stage, 20 key drivers of the research were extracted through literature review and interviews with banking and technology experts. After screening with the fuzzy Delphi method, 8 factors were removed and the rest were evaluated with the Marcus decision making technique. The findings of the research show that the two factors of "technology regulation" and "technology transfer costs" were chosen as key uncertainties for developing research scenarios. Based on these two key uncertainties, four scenarios were developed based on interviews with the focus group with the titles of comprehensive banking, static banking, searching banking, wandering banking. In the comprehensive banking scenario, everything is in its optimal state; Technology transfer costs have decreased and regulators are supportive of the technologies. According to the findings of the research, considering drivers, key uncertainties and alternative scenarios by managers and decision makers can improve the performance and increase the competitive advantage of banks.IntroductionFinancial innovations has been challenged the banking sector and can improve it. They cover a variety of financial businesses such as online lending, asset management platforms, trading management, mobile payment platforms, etc. All these services generate a large amount of data every day (Hasan et al, 2020: 1). Analyzing this volume of data is difficult, giving rise to the concept of "big data" (Munawar et al, 2020: 2). Big data as one of the important fields of future technology has attracted the attention of various industries (Raguseo & Vitari, 2018: 5206). In general, big data refers to a large volume of structured or unstructured data that is generated and stored at a high speed (Dicuonzo et al, 2019: 41). Big data has found its position in the banking industry; Because of the useful data they have stored in recent years (Rakhman et al, 2019: 1632). Recent applications of big data in banking have been for improving customer relationship management, marketing, optimizing strategic management and human resources (Parmar, 2018: 33; Hassani et al, 2018: 2). Therefore, it can be said that nowadays big data plays a major role in providing financial and banking services, and the realization of its potential benefits in banking is more from technical aspects and affects the organizational structure of banking and mobilizes a large number of different actors (Diniz et al, 2018: 151- 152). With changes in customer expectations and increased competition, the banking industry is no longer able to ignore technological innovations in the banking sector. Due to the numerous applications and benefits of big data in various industries, including the banking industry, and it's becoming more widespread in the future, this technology is becoming a prominent research topic (Phan & Tran, 2022: 6.)Research Question(s)What are the plausible scenarios for banking in Iran with an emphasis on big data? Literature ReviewMany studies conducted in the field of banking and big data deal with the role of big data in improving the performance of the banking industry (for instance: Shakya & Smys, 2021; Gonsalves & Jadhav, 2020; Hung et al, 2020; Parmar, 2018). Also, another part of the studies conducted with a future research approach in the banking sector without focusing on innovative financial technologies and specifically big data (for instance: Baumgartner & Peter, 2022; Eskandari et al,2020). The focus on innovative banking and financial technologies with a Futures Studies approach has been weak (for instance: Maja & Letaba, 2022; Murinde et al, 2022; Hajiheydari et al, 2021; Broby, 2021; Harris & Wonglimpiyarat, 2019). And the role of big data in the Futures Studies of the banking industry has been seen to be very limited due to the relatively large amount of data available in banks and its effect on performance and gaining a competitive advantage (for instance: Valero et al, 2020). Therefore, despite the studies conducted in the field of banking and big data, some of these researches have paid attention to the present time, and the researches conducted in the future of the banking industry have also been without focusing on the role of big data. Now, the most important theoretical gap in research is the lack of studies on the future of banking in Iran with an emphasis on big data. MethodologyThe current research is pragmatism due to the use of qualitative and quantitative methods from the perspective of philosophical foundations. It is also exploratory in terms of purpose due to the identification of drivers and practical in terms of direction due to the application of the results in the analysis of the future of banking in Iran. In the current research, two methods of literature review and interviews with experts are used to identify drivers, both of which are qualitative methods. According to Popper, the interview tool is based on the expert dimension. The literature review is evidence-based and uses articles and scientific texts to identify factors. Fuzzy Delphi, which is semi-quantitative and evidence-based, is used to screen and determine key drivers that require great accuracy. Then, to determine the key uncertainties, the MARCOS technique is used based on the importance and uncertainty indicators of the Global Business Network (GBN) approach, which is a quantitative and evidence-based technique. Finally, interviews with focus groups are used to write the scenario, which is a qualitative method based on the expert dimension. The theoretical community of the research includes academic experts and managers of the banking sector and are aware of new banking and financial technologies (Fintechs) and specifically big data. The selection of the participants is based on their knowledge and nobility of the research topic and the importance of their presence in the research, and finally 15 people were selected by purposeful sampling using the snowball method. Experts have at least 10 years of relevant work experience and a master's degree. ConclusionThis research has clarified the situation of this area by identifying the shaping factors and drivers of the future of banking in Iran. Two factors of "technology regulation" and "technology transfer costs" were chosen as key uncertainties for developing research scenarios. Based on these two key uncertainties, four scenarios were developed based on interviews with the focus group with the titles of comprehensive banking, static banking, searching banking, wandering banking. In the comprehensive banking scenario, everything is in its optimal state; Technology transfer costs have decreased and regulators are supportive of the technologies. Considering drivers, key uncertainties and alternative scenarios by managers and decision makers can improve the performance and increase the competitive advantage of banks.Keywords: Futures Studies, Driver, Scenario Planning, Banking, Big Data.
Data science, intelligence and future analysis
Mozhdeh Salari; Reza Radfar; Mahdi Faghihi
Abstract
AbstractThe purpose of this research is to investigate the effective factors in predicting the academic performance of undergraduate students in the classification of four classes. To achieve this goal, the study follows the CRISP data mining method. The data set was extracted from the NAD educational ...
Read More
AbstractThe purpose of this research is to investigate the effective factors in predicting the academic performance of undergraduate students in the classification of four classes. To achieve this goal, the study follows the CRISP data mining method. The data set was extracted from the NAD educational system for the bachelor's degree in Shahed University for the entry of the years 2011 to 2021. 1468 records were used in data mining. First, the effective features on students' academic performance were extracted. Modeling was done using Rapidminer9.9 tool. To improve classification performance and satisfactory prediction accuracy, we use a combination of principal component analysis combined with machine learning algorithms and feature selection techniques and optimization algorithms. The performance of the prediction models is verified using 10-fold cross-validation. The results showed that the decision tree algorithm is the best algorithm in predicting students' performance with an accuracy of 84.71%. This algorithm correctly predicted the graduation of 77.88% of excellent students, 85.26% of good students, 84.69% of medium students, and 85.96% of weak students based on the final GPA. IntroductionThe main problem in this research is to identify the factors that are effective in predicting the academic performance of undergraduate students in Shahed University. Choosing the best machine learning algorithm in predicting academic performance among different modeling methods based on validation and evaluation of models is another issue in the present research. The purpose of this research is to investigate the effective factors in predicting the academic performance of undergraduate students in Shahed University using educational data mining based on classification models.Research questionsThe main question in this research is what factors affect the prediction of undergraduate students' performance and improving their performance?Sub questions1- Which modeling algorithms have better results in predicting student performance?2- What methods have been used to predict students' performance?3- What is the validity of the developed model for Shahed University students? 2- Research background1-2- Theoretical foundationsEducational data miningThe processing of educational data improves the prediction of student behavior and new approaches to educational policies (Capuano & Toti, 2019) (Viberg et al., 2018)Academic performanceAcademic performance of students means the extent to which they achieve educational goals (Banik & Kumar, 2019).2-2- review of past studiesThe highlighted cells in Table 1, based on past research, show the classification algorithms that have the most accuracy and effectiveness in predicting students' performance in the relevant research. The decision tree algorithm has been used the most in previous researches. The NB algorithm has been the most used in research after the decision tree. RF and ANN algorithms are next in use. After that, SVM and KNN algorithms have been used in researchTable 1. The results of research literature based on the use of classification algorithmsData mining algorithmDTRFNBKNNSVMANNLine RLLRAccuracy(Batool et al., 2023) * * (Marjan et al., 2023)****** (Abdelmagid & Qahmash, 2023) * ** * (Manoharan et al., 2023)** * * * (Alghamdi & Rahman, 2023)*** 99.34%(Alboaneen et al., 2022) * **** (Yağcı, 2022)* *** *70-75%(Dabhade et al., 2021)* * * 83.44%(Najafi & etal,2021)* 95%(Soltani & etal,2021)* ** (Cruz-Jesus et al., 2020) * ** *50-81%(Sokkhey & Okazaki, 2020)*** * (Rebai et al., 2020)** (Jayaprakash et al., 2020)*** (Zulfiker et al., 2020)** * (Musso et al., 2020) * (Waheed et al., 2020) * 85%(Salal & Abdullaev, 2019)* **** (Turabieh, 2019)* ** * (Xu et al., 2019)* ** (ghodoosi & etal,2019)* * (fadavi & etal,2019) * 95.84%(Ajibade et al., 2019)* *** 91.5%(Ahmad & Shahzadi, 2018) * 85%(Hasani & Bazrafshan, 2018)* * (Hussain et al., 2018)*** * (Umer et al., 2017)**** * (Khasanah, 2017)* * (Asif et al., 2017)* (Hoffait & Schyns, 2017) * * *92.34%(khosravi &etal,2017)* * (Mueen et al., 2016)* * * 86%(Amrieh et al., 2015)* ** (Yehuala, 2015)* * 92.34%(zahedi & etal,2015)* * * (Punlumjeak & Rachburee, 2015)* (Osmanbegović et al., 2014)** 71%(Shamloo & et al.,2014)* (Asadi & et al.,2013)* (Kabakchieva, 2013)* ** 60-75%(Oskouei & Askari, 2014)*** * 96%(Nghe et al., 2007)* * present research****** 94.17%3- MethodThis study follows the popular training data mining method CRISP. The data collection of Nad educational system for bachelor's degree in non-medical fields of Shahed University has been extracted from 2011 to 2021. We used the Label Encoder technique to encode the features. In this research, C4.5 and ID3 decision tree classification algorithms, random forest, Naïve Bayes, k-nearest neighbor and artificial neural network and gradient enhanced tree were used to analyze and classify students and predict the final GPA. Modeling was done using RapidMiner 9.9. To improve the classification performance and solve the misclassification problem, we use a combination of principal component analysis and feature selection techniques and optimization algorithms. In this research, prediction accuracy was evaluated using 10-fold cross-validation method for all algorithms. Also, different algorithms were compared using the analytical descriptive method and based on evaluation criteria, and the best prediction model was introduced in this research.4-Data analysis4-1 IntroductionThe best model is the model that has the best values for the selected performance measurement criteria(Lever et al., 2016). Figure 1 is a graph that compares the accuracy of the algorithms used in this research.Figure 1. Comparative chart of the accuracy of the algorithms According to Table 2, the DTC4.5 algorithm is able to predict the class of 1235 objects out of 1458, which gives it an accuracy value of 84.71%.Table 2. Confusion matrix of DT C4.5-GI&OSE research modelprecisionStudents with poor performanceStudents with average performanceStudents with good performanceStudents with excellent performance 78.64%002281Prediction 178.67%94929522Prediction 286.46%50498271Prediction 389.36%3614120Prediction 4 85.95%84.69%85.26%77.88%Recall4-2 important featuresThe prioritization of predictive variables based on their weight is as follows:Diploma GPA: 0.262Semester 1 GPA: 0.201Semester 2 GPA: 0.197Number of honors semesters: 0.122Conditional number: 0.114Year of entry: 0.1044-3 The results of the implementation of the student performance prediction modelThe results of the prediction model are shown in Table 3:Table 3. The results of the DT C4.5-GI&OSE model implementation 5- DiscussionIn the main method of research, namely DT C4.5-GI&OSE, in the classification mode of four classes, it is observed that the average of the diploma has the greatest effect on the process of predicting student performance. In response to the sub-question of a research, the best algorithm in the four-class mode is Decision Tree C4.5-GI&OSE with a prediction accuracy of 84.71. This model showed 84.17% accuracy, 83.42% sensitivity and 0.780 kappa. DT C4.5-GI&OSE technique correctly predicted the graduation of 77.88% of excellent students, 85.26% of good students, 84.69% of average students, and 85.96% of poor students.6-ConclusionThe obtained results show that there is a relationship between students' social and academic characteristics and their academic performance. DT C4.5-GI&OSE algorithm was the best algorithm for predicting the final GPA scores of students at the end of studies with a prediction accuracy of 84.71%. In this model, the average grade point average of the diploma has the greatest effect on the prediction process. Using machine learning models as a decision support tool improves the academic level of students and reduces the number of potential unsuccessful and dropout students. This study was carried out at the undergraduate level, which can be used in future research for the master's and doctoral level.Keywords: student performance prediction, data mining, machine learning, modeling, improving the quality of education
Data science, intelligence and future analysis
mehdi mohammadiraz; maryam sharif nejad; Mohammad Hassan Fotros
Abstract
AbstractAmong the growth and development of businesses, managing financial flows and increasing its effectiveness is an important achievement that causes value stability, efficiency of systems and procedures throughout the chains of Business. Therefore, paying attention to uncontrollable and controllable ...
Read More
AbstractAmong the growth and development of businesses, managing financial flows and increasing its effectiveness is an important achievement that causes value stability, efficiency of systems and procedures throughout the chains of Business. Therefore, paying attention to uncontrollable and controllable variables that lead to value creation is inevitable. The purpose of this study is to study the impact of social and biological factors (production and recycling of polymer parts) of environment on the value creation of the company along the supply chain. Also the key role of financial ratios has also been considered in this regard.The present research is of quantitative and applied types and is based on mathematical modeling. It is the result of a combination of genetic algorithms and Simulated Annealing. The financial analysis parameters of the model include current ratios, debt to equity, Instantaneous ratio, net profit margin, cash ratio and rate of return. The analysis of the results shows that considering financial goals and indicators leads to improved profitability and by removing financial indicators from the model, profitability is reduced. Therefore,this is means that the environmental and social performance of the supply chain is improved.Companies can pay special attention to social issues and environmental factors along with their profitability Increase their economic value. Profitability can also be improved by exposing social responsibilities and the mission of environmental protection.IntroductionAmong the growth and development of businesses, managing financial flows and increasing its effectiveness is an important achievement that causes value stability, efficiency of systems and procedures throughout the chains of Business. Therefore, paying attention to uncontrollable and controllable variables that lead to value creation is inevitable. The purpose of this study is to study the impact of social and biological factors (production and recycling of polymer parts) of environment on the value creation of the company along the supply chain. Also the key role of financial ratios has also been considered in this regard.The present research is of quantitative and applied types and is based on mathematical modeling. It is the result of a combination of genetic algorithms and Simulated Annealing. The financial analysis parameters of the model include current ratios, debt to equity, Instantaneous ratio, net profit margin, cash ratio and rate of return. The analysis of the results shows that considering financial goals and indicators leads to improved profitability and by removing financial indicators from the model, profitability is reduced. Therefore,this is means that the environmental and social performance of the supply chain is improved.Companies can pay special attention to social issues and environmental factors along with their profitability Increase their economic value. Profitability can also be improved by exposing social responsibilities and the mission of environmental protection.Literature ReviewIn the literature review of the research, various factors such as economic issues, laws and regulations, social responsibility, and stakeholder pressures have been given as drivers to lead organizations to implement sustainable supply chain management infrastructure. In some cases, issues such as climate change,factors related to environmental issues and social parameters are ignored. This factor caused criticism in the conventional accounting topics and the topic was raised under the title of environmental management accounting and sustainability, environmental and social accounting) Schaltegger et al. 2013(. The drivers of the organization's movement towards a sustainable supply chain are different from the point of view of the final customer, government institutions, private organizations and legislative institutions. Laws and regulations are the main driver that dictates environmental issues to organizations. On the other hand, some organizations implement these laws in order to increase profitability or customer requests (Ko,Evans et al., 2016). The market and competitors are one of the drivers of the organization towards the adoption of sustainable supply chain management. In today's global business, the competition between organizations is very intense, and in order to impress customers, organizations need to put themselves in a position of superiority over their competitors. Being environmentally friendly and adapting to environmental requirements and paying attention to the organization's social responsibilities is a way to differentiate from other competitors. If competitors have benefited from sustainable supply chain management, the company will be under more pressure to establish sustainable supply chain management(Jian Zhang et al., 2021). In another article, it is suggested that through research in the field of supply chain management and corporate social responsibility, a hierarchical structure of supply chain management is proposed and a multipurpose measurement scale is presented to show the specific management practices of supply chain management(Zhang et al., 2019).MethodologyThe research methodology and the stages of its completion are in the category of quantitative and applied research. Considering that the purpose of applied research is to improve the product or process and test theoretical concepts in real problem situations, the purpose of this research is also to develop practical knowledge in the field of investigating the effects of environmental performance and social parameters along with financial flows on the profitability of the company and its chains. The supply is stable. Therefore, while studying the theoretical background of the research, the research problem is firstly expressed conceptually and then by means of a mathematical model, and in the next step, the mathematical model is solved and the data and results are analyzed. Research data is collected by field method and interviews with experts. To solve the model, the memetic hybrid algorithm has been used.ResultsIn this research, a three-objective mixed integer linear programming model for optimizing financial flows in a sustainable supply chain was presented. The goals of the model include three economic, social, bio-environmental and financial dimensions, and the functions of each are complementary. Although these dimensions depend on each other and affect the performance of others, it is necessary to make a single decision and manage how to implement each of these dimensions in a way that has the highest efficiency. Based on the surveys and analyzes of the research and its results, we state that paying attention to economic goals and financial factors leads to the improvement of profitability. On the other hand, if in the supply chain we only seek to improve the functioning of the environment and social factors, the profitability of the profit-making unit will decrease. In this research, we examined the simultaneity of the mentioned factors in order to realize more value and to improve the financial flows in the supply chain, we analyzed the different financial ratios that are needed by the decision makers in each organization.To analyze the sensitivity of the model, the waste loss rate index was used and it was observed that no matter how much the product loss rate increases in the collection of waste, it causes the profit function to decrease accordingly. The same issue has been proven to reduce negative environmental and social effects.
Data science, intelligence and future analysis
Mohammad Hoseini Moghadam
Abstract
The touch of the product plays an important role in the final decision of the customer when purchasing from physical and online retail, and the sensations that come to be enjoyed through touch enable them to experience the product from all angles. Therefore, considering the importance of touch, ...
Read More
The touch of the product plays an important role in the final decision of the customer when purchasing from physical and online retail, and the sensations that come to be enjoyed through touch enable them to experience the product from all angles. Therefore, considering the importance of touch, this research has investigated the lived experience of touching the product from the point of view of customers of physical and online stores. The following article is done with qualitative method and phenomenological paradigm. The research community is made up of electronic and clothing buyers from online and physical stores: Technolife, Adak, Havadar and Happyland in Tehran, and through semi-structured interviews, evidence was collected based on the purposeful sampling method. The interviews continued until reaching the theoretical saturation, and in this research, the interviews reached saturation with 15 people. Based on the extracted results, the main themes include; Product perception is physical touch, virtual touch, touch experiences, need for touch and touch perceptions. According to the results, managers of physical and online stores should provide conditions (such as the use of modern technologies) that touch and contact with the product happen to both groups of online and physical buyers so that they can buy products based on their needs and wants, and also this research can pave the way for the development of touch literature for researchers.IntroductionThroughout human history, the idea of progress has been a central concern for thinkers and intellectuals, with technological advancements playing a pivotal role in shaping the development of societies (Du Pisani, 2006; Rivers, 2002). Artificial intelligence (AI), as a driving force behind the fourth industrial revolution, has had a profound impact on numerous fields, including scientific research and discovery (Velarde, 2020). AI has revolutionized scientific knowledge to such an extent that distinguishing between the discoveries made by intelligent machines and human experts has become increasingly difficult (Krenn et al, 2022). This article explores the implications of AI for the future of scientific progress and its potential to give rise to post-normal science.Here is my attempt at rewriting the text as a senior researcher:The central question examined in this article is: what role does AI play in shaping the future of scientific developments? In exploring this overarching question, several related questions are also considered: How can AI be leveraged to uncover and obtain new scientific knowledge? Can novel computing techniques based on AI not only detect unusual patterns and events in data, but also lay the groundwork for new scientific advances? Might AI furnish new theories and transform our comprehension of science? Can AI-based scientific systems determine which scientific questions are worthwhile, and for whom are they valuable? Looking ahead, what assurances will scientists have about the validity of AI-based analyses in science?In response to these pressing questions, the core hypothesis presented is that AI has become the foundation for the emergence of a new breed and style of scientific discovery, which can be characterized as post-normal science. To evaluate this hypothesis, the historical background of relevant research is reviewed. AI represents a seismic shift in the practice of science, enabling analyses and discoveries that would be impossible for humans alone. While promising, it also poses troubling philosophical questions about the nature of truth and scientific understanding.MethodologyA variety of research methods were employed to address the questions raised in this study, including a systematic review of relevant literature to identify the transition from normal to post-normal science, trend analysis to examine the influence and expansion of AI in scientific discoveries, documentary studies to obtain theoretical and conceptual foundations, and modeling to understand and describe the progress of post-normal science under the influence of AI.FindingsAI has facilitated a new model of scientific discovery, known as data-driven scientific discovery, which derives hypotheses from data rather than relying on preconceived assumptions (Wheeler, 2004). This approach has transformed traditional sciences into data sciences, with scientific patterns extracted from data and an increasing focus on intelligent automation in scientific progress (King & Roberts, 2018). As a result, a new type of epistemology has emerged, characterized by the involvement of machines in scientific discovery and the advancement of the science cycle. This development, referred to as "Science 0.4" or the fourth type of science, has integrated science into society, enabling every citizen to participate as a scientist and fostering a shift towards "open science" (Odman & Govender, 2021).AI's impact on scientific research has been guided by several key principles, including sustainability, different forms of knowledge, accountability and responsibility, values and interests, collective wisdom and rationality, and non-determinism and non-linearity in the process of scientific discovery. AI has contributed to the realization of post-normal science by facilitating simulation and modeling, improving decision-making, promoting ethics, embracing diversity, fostering interdisciplinary collaboration, expanding stakeholder engagement, and enabling big data analysis.ConclusionAI systems have fostered interdisciplinary collaborations and facilitated the integration of knowledge and expertise across various fields, allowing for the identification and resolution of complex, interdisciplinary scientific issues. This collaboration disrupts the linear progression of normal science, promoting a more integrated and cooperative approach to problem-solving. Furthermore, AI has introduced new ethical and social considerations in scientific research, necessitating a departure from conventional forms of normal science. Although it remains uncertain whether AI will replace the human role in scientific discovery, it is clear that scientists and institutions that embrace AI technology will surpass those that do not.RecommendationsTo achieve excellence in the field of AI within scientific institutions, it is crucial to understand the "state of maturity in AI" and to establish a starting point for the governance system of science and its actors. In this process, scientific institutions can be categorized along a spectrum, ranging from those seeking to familiarize themselves with AI-driven changes in scientific discovery to those actively leveraging AI technology to advance scientific knowledge.Keywords: Artificial Intelligence, Normal Science, Post Normal Science, Science Progress, Scientific Discoveries.
Data science, intelligence and future analysis
Mehdi Fasanghari; Mohammad Asarian
Abstract
The fifth-generation networks of smart manufacturing and smart factory is rapidly evolving as a technology that integrates industrial production and smart Internet, bringing new support for the digital transformation of the industry and the development of a high-quality economy. Therefore, this ...
Read More
The fifth-generation networks of smart manufacturing and smart factory is rapidly evolving as a technology that integrates industrial production and smart Internet, bringing new support for the digital transformation of the industry and the development of a high-quality economy. Therefore, this article, with emphasis on the fifth generation of the Internet and with the aim of identifying 5G-based intelligent manufacturing projects, seeks to prioritize these projects using the hierarchical analysis method. Therefore, after reviewing the literature and interviewing with 17 experts, 5 main criteria for project prioritization were selected and weighted by AHP method using an expert questionnaire. Then, using the opinions of experts, 22 identified smart factory projects were prioritized according to the criteria weight. The criteria were calculated according to the income, cost and risk level of the project. Also Intelligent production line, intelligent logistics, intelligent resource allocation and process automation were identified as the most important intelligent production projects.IntroductionPrompt technological progress is driving a substantial paradigm shift in the manufacturing sector, empowering manufacturers to innovate and better satisfy consumer needs. In order to maintain a competitive edge on an international scale, manufacturers must implement technological advancements such as flexible production, robotics, automation, and smart factories to reduce expenses and increase efficiency (M Attaran & Attaran, 2020; Mohsen Attaran, 2023).5G technology is integrating intelligent internet with industrial production at an accelerated rate. Its provision of superior network services, including ample bandwidth, extensive connectivity, minimal latency, and dependable performance, serves as a catalyst for the advancement of the wireless industrial internet (Agiwal et al., 2016; Zhang et al., 2022)With augmented reality, artificial intelligence, and automation, 5G enables smart factories to perform troubleshooting (Wang, 2021). It addresses production obstacles while improving connectivity, speed, and quality (Yit et al., 2020). By facilitating intelligent management and agile production, 5G IoT provides factories with increased flexibility, reduced change turnaround times, and enhanced cost-effectiveness. It centralizes product lifecycle management, enhances communication, and streamlines smart factory operations (Siddiqui et al., 2022).5-G improves smart manufacturing by enabling real-time machine-to-machine communication, connectivity, and smart factory capabilities (Gangakhedkar et al., 2018). Early adoption of 5G has limited commercial applications in manufacturing, despite its potential (Wang, 2021). This article uses research, expert interviews, and project prioritization criteria to identify promising 5G applications in smart factories to aid 5G adoption decisions.Literature Review2.1. The fifth generation of mobile networksAmong the continuously evolving communication technologies, 5G emerges as a transformative entity. It follows the digitization of voice in 2G, the incorporation of multimedia in 3G, and the introduction of high-speed wireless broadband in 4G, constituting the fifth generation of mobile networks. Present communication technologies are facing challenges in keeping pace with the exponential growth of demand for mobile services, communication capabilities, and network traffic (Mu et al., 2020).5G, designated IMT-2020 by the International Telecommunication Union in 2015, will revolutionize connectivity and capabilities. Its features include user-centric network architecture, cloud radio access network architecture, beamforming antennas, millimeter-wave hybrid and standalone networks, and user plane separation. 5G offers over 1000-fold increased communication capacity, 10-100 times faster data transfer speeds, less than 1 millisecond latency, 10-100 times larger large-scale connectivity, lower costs, and a vastly improved user experience (Agiwal et al., 2016; Alqahtani et al., 2023; Li et al., 2020).2.2. Smart factorySmart manufacturing, or smart factories, uses 5G technology to improve efficiency, reduce production time, and optimize processes. It uses smart sensors to monitor and control production. These sensors can adapt to external stimuli, make logical decisions, and relay information, enhancing manufacturing efficiency and intelligence (Hozdić, 2015; Soori et al., 2023; Temesvári et al., 2019; Zuehlke, 2010).2.3. Smart manufacturing technologiesM2M and D2D communication are part of smart manufacturing. Active communication, data-driven decision-making, and control commands are enabled by M2M connections between humans, machines, and systems. It helps implement IoT smart connections. Conversely, D2D allows peer devices in a network to communicate directly. Communication is routed and managed autonomously by each device, optimising resource usage and network efficiency to improve connectivity (Ding & Janssen, 2018).2.4. Smart officeThe impact of 5G technology transcends the boundaries of the manufacturing facility. It enables employees to optimize their productivity by means of virtual assistants, digital communication tools, and rapid data transfer, thereby empowering intelligent workplaces. The realization of a mobile digital office is facilitated by 5G, which also promotes employee collaboration, adaptability, and uninterrupted communication (M Attaran & Attaran, 2020; Rao & Prasad, 2018).2.5. Automation and supply chain management and 5GBy facilitating communication and data exchange between and within organizations, 5G has a substantial effect on supply chain management. By improving the ability to integrate suppliers, customers, and internal logistics processes, it grants organizations a competitive edge. 5G enhances the overall efficiency of supply chains through the optimization of processes, reduction of costs, improvement of quality, and implementation of real-time monitoring capabilities (Liu, 2021; Rejeb & Keogh, 2021; Taboada & Shee, 2021).2.6. BlockchainBlockchain is a decentralized, global technology that works like a "large computer." It processes digital asset transactions like money, personal data, health records, and others as a distributed ledger. Blockchain accelerates computation through encryption and data improvement. Blocks of transaction records form a blockchain, ensuring data integrity. Blockchain combined with 5G technology allows real-time ownership and location tracking, improving transparency, validating products, preventing fraud, and improving supply chain efficiency. Monitoring KPIs ensures network performance transparency and ensures material sourcing, manufacturing, and supply chain security (Han et al., 2023; Jovović et al., 2019; Tahir et al., 2020).MethodologyThis study uses pragmatism-based applied research. Its main goal is to identify 5G network projects and applications in smart factories. The study is mixed-method, using qualitative and quantitative methods.First, 5G in smart factory projects literature was reviewed and expert interviews were conducted to identify relevant projects. These projects were refined using content analysis.17 industry experts were interviewed to evaluate and prioritize the projects in the second phase. After statistical analysis, 31 projects were reduced to 17. After comparing these projects to the literature, 22 were chosen.The third stage involved choosing five project evaluation and weighting criteria. The 17 experts were given a questionnaire to weight each criterion by importance.The fourth stage scored projects using the five criteria. Our Analytic Hierarchy Process (AHP) determined each project's final weight and ranking. The Analytic Hierarchy Process helps decision-makers prioritize options in complex and uncertain situations. It organises factors into a hierarchical tree structure and solves decision-making problems by breaking down large problems into smaller ones. This method clarifies problem relationships and concepts.ConclusionThe 5G wireless communication technology has emerged as an indispensable component in the advancement and administration of intelligent manufacturing. Exploring the applications of 5G connectivity in smart factories, this study seeks to identify projects that are feasible. By conducting interviews with IT specialists and reviewing prior articles in this field, the research identified 22 implementable projects. The prioritization of these projects was determined by the following five factors: total project cost, project revenue, social benefits, project feasibility, and project risk level. The findings indicated that project revenue was the most pivotal criterion, with project cost and risk level following suit. Both intelligent logistics and smart production lines, which are the top two recommended project categories, stand to gain substantially from 5G integration. Additionally, intelligent supply chain management, intelligent resource allocation, and process automation are crucial initiatives that can augment smart manufacturing.Keywords: Fifth-generation internet wireless mobile communications (5G), Analytic Hierarchy Process (AHP), Smart factory, Smart manufacturing, Technology.The fifth-generation networks of smart manufacturing and smart factory is rapidly evolving as a technology that integrates industrial production and smart Internet, bringing new support for the digital transformation of the industry and the development of a high-quality economy. Therefore, this article, with emphasis on the fifth generation of the Internet and with the aim of identifying 5G-based intelligent manufacturing projects, seeks to prioritize these projects using the hierarchical analysis method. Therefore, after reviewing the literature and interviewing with 17 experts, 5 main criteria for project prioritization were selected and weighted by AHP method using an expert questionnaire. Then, using the opinions of experts, 22 identified smart factory projects were prioritized according to the criteria weight. The criteria were calculated according to the income, cost and risk level of the project. Also Intelligent production line, intelligent logistics, intelligent resource allocation and process automation were identified as the most important intelligent production projects.IntroductionPrompt technological progress is driving a substantial paradigm shift in the manufacturing sector, empowering manufacturers to innovate and better satisfy consumer needs. In order to maintain a competitive edge on an international scale, manufacturers must implement technological advancements such as flexible production, robotics, automation, and smart factories to reduce expenses and increase efficiency (M Attaran & Attaran, 2020; Mohsen Attaran, 2023).5G technology is integrating intelligent internet with industrial production at an accelerated rate. Its provision of superior network services, including ample bandwidth, extensive connectivity, minimal latency, and dependable performance, serves as a catalyst for the advancement of the wireless industrial internet (Agiwal et al., 2016; Zhang et al., 2022)With augmented reality, artificial intelligence, and automation, 5G enables smart factories to perform troubleshooting (Wang, 2021). It addresses production obstacles while improving connectivity, speed, and quality (Yit et al., 2020). By facilitating intelligent management and agile production, 5G IoT provides factories with increased flexibility, reduced change turnaround times, and enhanced cost-effectiveness. It centralizes product lifecycle management, enhances communication, and streamlines smart factory operations (Siddiqui et al., 2022).5-G improves smart manufacturing by enabling real-time machine-to-machine communication, connectivity, and smart factory capabilities (Gangakhedkar et al., 2018). Early adoption of 5G has limited commercial applications in manufacturing, despite its potential (Wang, 2021). This article uses research, expert interviews, and project prioritization criteria to identify promising 5G applications in smart factories to aid 5G adoption decisions.Literature Review2.1. The fifth generation of mobile networksAmong the continuously evolving communication technologies, 5G emerges as a transformative entity. It follows the digitization of voice in 2G, the incorporation of multimedia in 3G, and the introduction of high-speed wireless broadband in 4G, constituting the fifth generation of mobile networks. Present communication technologies are facing challenges in keeping pace with the exponential growth of demand for mobile services, communication capabilities, and network traffic (Mu et al., 2020).5G, designated IMT-2020 by the International Telecommunication Union in 2015, will revolutionize connectivity and capabilities. Its features include user-centric network architecture, cloud radio access network architecture, beamforming antennas, millimeter-wave hybrid and standalone networks, and user plane separation. 5G offers over 1000-fold increased communication capacity, 10-100 times faster data transfer speeds, less than 1 millisecond latency, 10-100 times larger large-scale connectivity, lower costs, and a vastly improved user experience (Agiwal et al., 2016; Alqahtani et al., 2023; Li et al., 2020).2.2. Smart factorySmart manufacturing, or smart factories, uses 5G technology to improve efficiency, reduce production time, and optimize processes. It uses smart sensors to monitor and control production. These sensors can adapt to external stimuli, make logical decisions, and relay information, enhancing manufacturing efficiency and intelligence (Hozdić, 2015; Soori et al., 2023; Temesvári et al., 2019; Zuehlke, 2010).2.3. Smart manufacturing technologiesM2M and D2D communication are part of smart manufacturing. Active communication, data-driven decision-making, and control commands are enabled by M2M connections between humans, machines, and systems. It helps implement IoT smart connections. Conversely, D2D allows peer devices in a network to communicate directly. Communication is routed and managed autonomously by each device, optimising resource usage and network efficiency to improve connectivity (Ding & Janssen, 2018).2.4. Smart officeThe impact of 5G technology transcends the boundaries of the manufacturing facility. It enables employees to optimize their productivity by means of virtual assistants, digital communication tools, and rapid data transfer, thereby empowering intelligent workplaces. The realization of a mobile digital office is facilitated by 5G, which also promotes employee collaboration, adaptability, and uninterrupted communication (M Attaran & Attaran, 2020; Rao & Prasad, 2018).2.5. Automation and supply chain management and 5GBy facilitating communication and data exchange between and within organizations, 5G has a substantial effect on supply chain management. By improving the ability to integrate suppliers, customers, and internal logistics processes, it grants organizations a competitive edge. 5G enhances the overall efficiency of supply chains through the optimization of processes, reduction of costs, improvement of quality, and implementation of real-time monitoring capabilities (Liu, 2021; Rejeb & Keogh, 2021; Taboada & Shee, 2021).2.6. BlockchainBlockchain is a decentralized, global technology that works like a "large computer." It processes digital asset transactions like money, personal data, health records, and others as a distributed ledger. Blockchain accelerates computation through encryption and data improvement. Blocks of transaction records form a blockchain, ensuring data integrity. Blockchain combined with 5G technology allows real-time ownership and location tracking, improving transparency, validating products, preventing fraud, and improving supply chain efficiency. Monitoring KPIs ensures network performance transparency and ensures material sourcing, manufacturing, and supply chain security (Han et al., 2023; Jovović et al., 2019; Tahir et al., 2020).MethodologyThis study uses pragmatism-based applied research. Its main goal is to identify 5G network projects and applications in smart factories. The study is mixed-method, using qualitative and quantitative methods.First, 5G in smart factory projects literature was reviewed and expert interviews were conducted to identify relevant projects. These projects were refined using content analysis.17 industry experts were interviewed to evaluate and prioritize the projects in the second phase. After statistical analysis, 31 projects were reduced to 17. After comparing these projects to the literature, 22 were chosen.The third stage involved choosing five project evaluation and weighting criteria. The 17 experts were given a questionnaire to weight each criterion by importance.The fourth stage scored projects using the five criteria. Our Analytic Hierarchy Process (AHP) determined each project's final weight and ranking. The Analytic Hierarchy Process helps decision-makers prioritize options in complex and uncertain situations. It organises factors into a hierarchical tree structure and solves decision-making problems by breaking down large problems into smaller ones. This method clarifies problem relationships and concepts.ConclusionThe 5G wireless communication technology has emerged as an indispensable component in the advancement and administration of intelligent manufacturing. Exploring the applications of 5G connectivity in smart factories, this study seeks to identify projects that are feasible. By conducting interviews with IT specialists and reviewing prior articles in this field, the research identified 22 implementable projects. The prioritization of these projects was determined by the following five factors: total project cost, project revenue, social benefits, project feasibility, and project risk level. The findings indicated that project revenue was the most pivotal criterion, with project cost and risk level following suit. Both intelligent logistics and smart production lines, which are the top two recommended project categories, stand to gain substantially from 5G integration. Additionally, intelligent supply chain management, intelligent resource allocation, and process automation are crucial initiatives that can augment smart manufacturing.Keywords: Fifth-generation internet wireless mobile communications (5G), Analytic Hierarchy Process (AHP), Smart factory, Smart manufacturing, Technology.
Data science, intelligence and future analysis
Yaqub Ahmadlou; Alireza pourebrahimi; jafar tanha; Ali Rajabzadeh Ghatari
Abstract
Fraud cases have increased in recent years, especially in important and sensitive financial and insurance fields. Therefore, to deal with such frauds, there is a need for different measures than traditional inspection methods. Agricultural insurance is also not exempted from this threat due to its nature ...
Read More
Fraud cases have increased in recent years, especially in important and sensitive financial and insurance fields. Therefore, to deal with such frauds, there is a need for different measures than traditional inspection methods. Agricultural insurance is also not exempted from this threat due to its nature and wide extent and every year a lot of money is spent on paying fake damages. This research was presented with the aim of providing a model to discover unrealistic damage claims in agricultural insurance by using data mining and machine learning techniques. It was used to build a deep learning model. The data used was obtained from the Agricultural Insurance Fund and related to wet and rainfed wheat insurance policies of Khuzestan province, for which compensation was paid in the 2018-2019 crop year. After preparing and preprocessing the data, using deep learning to discover unusual cases, the action and results were evaluated by the experts of the Agricultural Insurance Fund. After analyzing the results, it was found that 1% of the damages paid were related to unrealistic requests and more care should be taken in paying the damages. The accuracy of the model in detecting unusual cases for wet and dry wheat was 53.53 and 63.37 percent, respectively. In the review of the results, it was found that 5 categories of unusual behavior have led to the payment of unrealistic damages, and the behavior of not providing damage documentation was more frequent than the others.IntroductionInsurance fraud refers to the immoral act of committing a crime with the intention of abusing an insurance policy to obtain illegal profit from an insurance company; In general, insurance is made to protect the assets and business of individuals or organizations against financial loss and may occur at any stage of the insurance process by anyone such as customers or fraudulent agents (Al -Hashedi & Magalingam, 2021). Insurance fraud not only reduces the profit of the insurance company and leads to major losses, but also affects the pricing strategy of the insurance company and its socio-economic benefits in the long term (Yaram, 2016). Every year, significant sums of money are defrauded from the insurance industry, but not all of them are discovered. According to the statistics published by the Insurance Anti-Fraud Coalition, an amount of about eighty billion dollars is added to customers' expenses in the United States through fraud, and they must compensate for the amount of fraud by paying higher insurance premiums in the following year (Fraud statistics, 2020). In Iran, there is no accurate estimate of the amount of compensations paid to unreal damage claims or any other fraud, and one of the goals of this research is to estimate the amount of fraud in wheat crop insurance using deep learning. Research Question(s)This research seeks to find answers to these questions: In rainfed and irrigated wheat crop insurance, what percentage of the paid compensations are related to unrealistic and fictitious damage claims, and what is the accuracy of deep learning detection for this purpose?Literature ReviewGhahari et al. (2019) in their study investigated the use of deep learning in predicting agricultural performance in time and space with unstable weather conditions. They compared the performance of machine learning next to weather stations with conventional methods. Their findings showed that deep learning provides the highest prediction accuracy compared to other approaches. It can also be inferred from this result that the use of deep learning can play a role in reducing agricultural insurance costs by knowing the exact measures of crop yield (Newlands et al., 2019). Gomez et al. (2021) presented a new deep learning method to gain pragmatic insight into the behavior of an insured individual using the unsupervised effective variable. Their proposed method can be used in the fields of pension insurance, investment and other broader areas of the insurance industry. Their proposed method enables auto encoder and variable auto encoder to be used in semi-supervised/unsupervised effective variable analysis to identify cheating agents (Gomes et al., 2021). Xia et al. (2022) in their study proposed a deep learning model to detect car insurance fraud by combining convolutional neural network, long-term and short-term memory, and deep neural network. In their proposed method, more abstract features were extracted and helped the experts in the complex process of feature extraction which is very critical in traditional machine learning algorithms. The results of the experiments showed that their method can effectively improve the accuracy of car insurance fraud detection.MethodologyThe current research method is practical from the point of view of the objective and is data-oriented from the point of view of its nature. For machine learning modeling, the standard CRISP process has been used, which includes the stages of data collection, data preparation and preprocessing, modeling and model evaluation, and obtaining results. Figure 1 shows the general process of anomaly detection and analysis.Figure 1. Anomaly detection process framework In this research, the data related to one agricultural year of wet and dry wheat crop were obtained from the Agricultural Insurance Fund. The national code of the insurers has been removed from the data set to maintain confidentiality. The extracted data is related to the crop insurance policies of wet and rainfed wheat for the crop year 2018-2019 of Khuzestan province. In this crop year, compensation has been paid for these insurance policies according to the claim of the damage they had, in other words, the data set includes those insurance policies of wet and dry wheat whose product is damage Seen and compensated for them. The data were obtained from the comprehensive system of the insurance fund in the form of a csv report. The obtained data set had 23 features.ConclusionThe results of the research show that in wheat insurance, about 1% of the compensations paid are allocated to unrealistic claims, so they need to be further investigated by experts before payment. This amount of compensations paid to unrealistic claims was close to the prediction of insurance fund inspection experts who stated that about 1.5% of claims are unrealistic. Also, according to the results, 5 categories of behavior or methods were identified in the beneficiaries to receive compensation for unrealistic claims, which are mentioned below:Lack of sufficient documentation to prove the damage: This means that the necessary documents that should be uploaded in the system according to the implementation methods are not available or some of them have not been uploaded. Payment of compensation without the existence of documents indicating the occurrence of damage can be caused by the negligence or collusion of the appraiser or broker with the insured.The documents are not in accordance with the declared damage: the documents uploaded in the system according to the relevant instructions do not show the occurrence of the type of registered damage. For example, the speed of storm damage is mentioned as 50 km/h, but in meteorological documents it is 15 km/h.The damage documentation is not true: for example, in some documents, the risk factor is mentioned in the expert form of drought, but the picture sent shows flood damage. In this case, it is probably due to negligence. In another possibility, it is also possible to send the image of damaged agricultural land instead of healthy agricultural land. Non-observance of the damage notification period: According to the executive instructions of the insurance fund, the time limit for the declaration of damage until the time of payment of compensation is one month. Outside of that, it is against the instructions. Sometimes it was observed that the damage had been declared before the accident. The date of damage does not match with the time of its announcement: according to the executive instructions of the insurance fund, in the case of damage to agriculture, the visit must be done one week after the occurrence of the damage; before removing the damage, the type and amount of the damage should be carefully checked. In some cases, it was observed that the announcement date was recorded one month after the damage occurred. It is clear that after removing the effects of damage, the payment of compensation can seem suspicious because there may not have been any damage in the past.Keywords: Anomaly Detection, Crop Insurance, Deep Learning, Auto Encoder.
Data science, intelligence and future analysis
Elmira Darzi; Mehrdad Agha Mohammad Ali Kermani; Mostafa Jafari
Abstract
Due to their temporary nature and precise time and cost planning, project organizations are more involved in the relationship between data and operational processes, which requires the correctness of the actual processes of the organization. On the other hand, one of the essential issues for managing ...
Read More
Due to their temporary nature and precise time and cost planning, project organizations are more involved in the relationship between data and operational processes, which requires the correctness of the actual processes of the organization. On the other hand, one of the essential issues for managing project-oriented organizations is its business process management, but due to the dynamic behavior and complexity of the nature of a project-oriented organization, identifying the processes through the traditional modeling of business process management is not reliable. The emerging solution to this problem is called "process mining." The paper introduces a framework that employs accurate process identification to measure the performance of business units relative to reality. This comprehensive framework undertakes the prerequisite steps of identification, including monitoring and cleaning the process-aware information systems' data to discover the process's current state and examine it from different perspectives based on the selected process. The primary purpose of this paper is to develop a framework for improving the P2P process in Chavosh Rah Company through process mining. The paper presents a framework to enhance the P2P process in project-oriented organization by implementing and extracting knowledge from the process, discovering unexpected and hidden relationships, and finding bottlenecks by employing process mining.
Introduction
Today, organizations must identify and manage their current processes for an effective approach. Workflow management systems are used to support business processes. Although current workflow management systems support the design, configuration, execution, and control of the processes under their control, there are deficiencies in the troubleshooting phase. Process mining is used to fill these gaps. Process mining is a bridge between data science and process science. The main aspects of process mining are the "discovery, monitoring, and improvement of real processes by extracting knowledge from event information" that is accessible in today's systems.
By evaluating real behaviors, process analysis provides a realistic view of operational processes, which is useful and important in developing support systems or redesigning previous processes. The purpose of process mining is to extract non-obvious and practical information related to processes from the event graph. The event log is actually the recorded data related to the events of the execution of a business process in an organization. One of the most important characteristics of an event diagram is that it is formed based on the events that happen. This means that regardless of how an organization's business process is planned or designed, the event graph contains data on how the process is implemented in reality.
Applications of process mining have been covering articles in the fields of health, information technology, finance, education, government affairs, energy, agriculture, logistics, public relations, media, and tourism. The purchase request process with the process analysis approach in the project organization is the innovation center of this article because no research has been done in line with this point of view. Of course, this article is a scientific and practical project. Naturally, the analyzes and results are based on the real data of each organization, which is usually different from other organizations, but by doing such a project, the obtained results can be generalized for organizations that have similar performance.
After the preparation of the event diagram, it is possible to define the APQC-approved relevant indicators in parallel with the start of the process analysis and analyze the organization from the perspective of these indicators. Then, with the help of interviews with the organization's experts who are involved in the purchasing process, improvement suggestions are collected and announced to the organization's management unit. The case study in this article is about the purchasing process of a contracting company. Chavosh Rah Bana Company was established in order to implement infrastructure projects in the fields of road construction, construction, and facilities. Shopping in Chavosh Rah Bana company includes the steps of registering a request, checking the request, checking the warehouse by the warehouse of the available goods, requesting a non-existent purchase, asking the price by the procurement unit, management approval, choosing the payment method and issuing a valid check or purchase, and finally registering a debt or registration It is creditable.
Research Question(s)
In this article, the following questions are raised, which we will try to answer by advancing the goals of the article had:
1) Does the mining process have a direct impact on the purchase request process?
2) Is time optimization effective in planning based on process analysis?
3) Is there a logical and acceptable answer in planning based on the use of real data? Will we reach the mining process?
4) Which is the most common path in the process?
5) In what order are the items (cases) distributed in the process?
6) How much do the cases conform to the process model? What problems are there?
7) What is the average/minimum/maximum operation time of the process?
8) Which of the tasks takes more time?
9) How are the cases actually implemented?
Literature Review
In the field of the purchasing process, two articles were studied, which are related to 2019 and 2018. The first article with the topic "Using process mining to find the main factors of delay in the internal purchasing process" was prepared by Virginia Eitzel Contras, Jesus Andres Portillo, and Fernando Gonzalez. In this article, the internal purchasing process of Quintal company was investigated. The software used in this article is Fluxicon Disco software. In this article, 608 cases (9199 events) were analyzed. The purpose of this paper was to increase the efficiency of Quintal's internal purchasing department through recommendations based on the analysis of their process reports.
The second paper "Process Mining Analysis of Purchasing Process in a Heavy Manufacturing Industry" was prepared by Chiwon Chu and Hind Rebigid. In this article, the purchasing process in a marine and ship parts manufacturing company in Korea was investigated. The software used in this article is Fluxicon Disco software. In this article, 663 cases (9829 events) were analyzed. This article identified the activities in which the process consumes a lot of time and also rework occurs in them.
In the review article on the application of process mining by Dakik et al., a review of the researches conducted on the subject of the applications of process mining until 2018 was done and the result was that the main use of process mining was in the fields of health, information technology, finance, production and It is education.
In 2018, Baykazoglu et al. published an article entitled "An approach based on process analysis to evaluate students' performance in computer tests". In this article, by tracing the logs of the students' journeys on the computer, the process of answering them has been discovered and analyzed.
The first study that used process mining to explore and analyze an inter-organizational process was conducted by VanderAalst in 2000. During this research, workflows between different organizations were modeled and analyzed. After that, an article on supply chain processes in the field of discovery of distribution processes in the supply chain was done by Maroster et al. in 2003.
In 2009, Garek et al. analyzed the RFID-oriented supply chain process. In this supply chain, the position of each item is tracked by its special code, and this makes it possible to get the most out of the mining process.
In 2014, Bernardi et al. discovered inter-organizational business rules through the data available in cloud data and by process mining. In 2014, Klaze et al. presented research on the integration of the event diagram of several different organizations to start process analysis.
Many researches have been conducted on the application of process mining for the three main actions of discovery, compliance review, and improvement. The literature review of this section includes all the books and articles published in the journal and some theses that have accurately used the words process analysis and performance or efficiency in their title. The first time that process mining has been introduced as a performance measurement methodology, Park et al. compared 19 block production processes in a Korean shipbuilding company by DEA. The main contribution and goal of their research is the development of one of the DEA models, and they used automatic process analysis results only to measure the 5 performance indicators they considered. The review goes under these subheadings.
In 2015, a part of Leer et al.'s book was published in Germany called Process Performance Evaluation. In this section, the process performance evaluation procedure is described as a part of the BPM cycle by introducing the generalities of process analysis and DEA along with an application example. Then in the same year in 2016, in his senior thesis at the University of Eindhoven in the Netherlands, van den Ing measured the performance of different paths of purchase-to-payment process in an organization.
Many articles have been published in the field of health in this regard. In 2019, Rojas et al. analyzed the performance of emergency room departments to help decision-makers improve the quality of medical center services. Also, using a case study of process mining, by extracting data from a hospital information system, Bettinni et al. The performance of this system was evaluated using the time indicators available in the process analysis tool. In 2020, Anastasia Pika and colleagues studied process mining to protect the privacy of people's information recorded in healthcare and analyzed data privacy and application requirements for healthcare process data.
In the field of the food industry, in 2021, Mathew Mastella investigated the process of mining in this industry. Also, in 2020, Peyman Badakhshan and his colleagues investigated the purchase order process with the help of mining in the paint industry.
Methodology
The main methodology proposed in this article is briefly and clearly presented in Figure 1. As can be seen, the access to the raw data available in the current software in the company is the starting point of this article. After that, the image of the event, which is considered the input of any process mining tool, should be extracted by monitoring the raw data of the systems, so that various process mining techniques can be applied to it. Discovery and analysis of the process in order to see the details of the process paths in the studied period by Behfaleb software is the next step. After preparing the event diagram, in parallel with the start of the process analysis, the relevant APQC-approved indicators can be defined and the organization can be analyzed from the perspective of these indicators. Then, with the help of interviews with the organization's experts who are involved in the purchasing process, improvement suggestions are collected and announced to the organization's management unit.
Figure 1. Methodology
Conclusion
In this article, it is focused on the application of process mining in the purchasing process of a project-oriented organization. The competitive conditions have forced contractor companies (project oriented) to manage their processes completely and to get help from strategic and operational tools to improve their performance. In this regard, the main goal of this article is to examine one of the important processes of the project-oriented company (purchasing process). For the case study, the data obtained from the purchase process of Chavosh Rah Bana's project-oriented company has been used. With the help of the obtained data, the purchase process of the company was extracted and analyzed from different perspectives. With the help of these analyses and the review of the time indicators introduced in APQC, suggestions for improvement were presented with the help of the company's expert group. Of course, these suggestions can be used in other project-oriented organizations that have a similar function to this type of organization. The suggestions are as follows:
1) Correct purchase planning
2) Having a vendor list of suppliers with relevant indicators
3) The flow of systemic thinking in the organization
4) Using people with expertise
5) Using the warning system to implement activities on time
6) periodic reporting and timely registration in the system
7) Increasing the number of personnel in the procurement unit
8) Teaching the principles and techniques of negotiation
Acknowledgments
We are very grateful to Behin Sazan Farayand Amin Knowledge Based Company, the developer of the first Iranian mining process tool (Bahfalab) for supporting this research. We also thank Mr. Engin
nization, Purchasing Process.
Data science, intelligence and future analysis
Monireh Hosseini; Elnaz Galavi
Abstract
Community detection is an important topic for social network analysis and is also essential to understanding complex networks structure. In community detection, the goal is to determine the groups in which the group nodes are densely connected to each other. In this research, deep learning techniques ...
Read More
Community detection is an important topic for social network analysis and is also essential to understanding complex networks structure. In community detection, the goal is to determine the groups in which the group nodes are densely connected to each other. In this research, deep learning techniques have been used to control graph data with high dimensions, while presenting a comprehensive and integrated architecture of community recognition methods with deep learning. Community detection classic approaches are suitable for networks with low dimensions. Therefore, the reduction of complex network dimensions is counted as a significant topic in community detection. In this paper, in order to reveal the direct and indirect connections among nodes, first a new similarity matrix of network topology is built. Then, a stacked auto-encoder is designed to decrease dimensions based on unsupervised learning. In order to detect communities, various clustering algorithms are then tested and utilized. Evaluation of the proposed research model is performed by surveying various experiments on standard criteria and six real data sets of Karate, Dolphins, Football, Polbooks, Cora and Citeseer. The proposed method evaluation outcomes show a higher accuracy in the identification of communities in the football data set compared to the twelve proposed algorithms used in past researches, and show a significant improvement in other data sets compared to the thirteen algorithms.
Introduction
Today, due to the increasing use of the Internet, social networks have found an important role in the real life of people. In social networks, some nodes are more connected than the entire network nodes, which are called communities(Sperli, 2019). Community Detection is an important topic for social network analysis and is also essential to understanding complex network structure In community detection, the goal is to determine the groups in which the group nodes are densely connected.
There are many methods for community detection, but deep learning has shown excellent performance in a wide range of research fields, such as social networks, graph embedding, etc.
In this research, deep learning techniques have been used to control graph data with high dimensions, while presenting a comprehensive and integrated architecture of community detection methods with deep learning.
Research Questions
Is it possible to create a new similarity matrix from the graph of complex networks that fully reveals the similarity relationships between network nodes?
What is the appropriate method of deep learning to represent the features of complex networks in low dimensions?
Is it possible to provide a suitable framework with model flexibility for networks of different sizes for community detection using the deep learning method?
Can more accurate clustering results be achieved for community detection?
Literature Review
2.1.Community detection classic approaches are suitable for networks with low dimensions. Therefore, the reduction of complex network dimensions is counted as a significant topic in community detection. The disadvantage of the high-dimensional network is the huge computational costs incurred by community detection methods. Therefore, a method is needed to transform high-dimensional graphs into a lower-dimensional space, where important information about network structure and node properties is still preserved. According to past research, autoencoders are the dominant method for mapping data points in lower-dimensional spaces (Souravlas et al, 2021).
2.2.To display the network, using the proximity matrix as the network similarity matrix can describe the similarity relationship between the nodes in the network. But the relationship between nodes in a social network is complex. On the other hand, in addition to the similarity between nodes that are directly connected, there are different degrees of similarity between nodes that are not directly connected (Su et al., 2020).
2.3. Wu et al. (2020) and Geng et al. (2020) reconstructed the adjacency matrix to represent the network. Dhilber and Bhavani (2020) used a cubic matrix for the input of the stack autoencoders, as did the work of Yang et al. (2016). Xie et al. (2018) first proposed a new representation of network similarity and then fed it with a sparse filtering model to extract meaningful features of network nodes. But in addition to the problem of lack of neighbor information in the proximity matrix based on Su et al.'s (2020) research, using only one function to check the similarity between nodes cannot fully reveal the topological information of the network. Therefore, a similarity matrix should be presented that can solve the proposed gaps.
Methodology
In this paper, to reveal the direct and indirect connections among nodes, first, a new similarity matrix of network topology is built. To construct the new similarity matrix, two matrices are used, i.e. proximity matrix and S∅rensen–Dice's (S∅) similarity matrix in Xie et al. (2018) 's research. In the next step to extract low-dimensional graph features, the new similarity matrix is given as input to the stack autoencoder networks, which have several hidden layers for unsupervised training. Then, using the newly learned features that are in the low-dimensional matrix with the help of K-means, DBSCAN, and SNNDPC clustering algorithms, communities are detected.
Conclusion
Evaluation of the proposed research model is performed by surveying various experiments on standard criteria and six real data sets of Karate, Dolphins, Football, Polbooks, Cora, and Citeseer. The proposed method evaluation outcomes show a higher accuracy in the detection of communities in the football data set compared to the twelve proposed algorithms used in past research and show a significant improvement in other data sets compared to the thirteen algorithms. In addition to these cases, the superiority of the similarity matrix used in this research was proved as a key prerequisite for community detection.
Keywords: Community Detection, Deep Learning, Autoencoder, Complex Networks.