Mojtaba Salehi; Fatemeh Garshasbi
Abstract
vStock market has been one of the most influential economic phenomena in the world for many years. The main players in the stock market are investors that are always looking to make the most profit. Since prices of stock market transactions is Impressionable from political, economic, social problems ...
Read More
vStock market has been one of the most influential economic phenomena in the world for many years. The main players in the stock market are investors that are always looking to make the most profit. Since prices of stock market transactions is Impressionable from political, economic, social problems and the high volatility of prices, the prediction of stock market is very difficult. The main solution for more profits in the market is making the right decisions about buying and selling appropriate stocks in appropriate time. Therefore, prediction is the most important requirements for traders. I this research, a new hybrid algorithm is proposed that uses imperialist competitive algorithm as a feature selection method and fuzzy adaptive neural inference system as a prediction function. This approach uses 63 features that affect the stock market, including economic features, Iran and other countries stock market indexes, technical analysis indexes and Japanese Candlestick on a daily basis in the period from 2010-2016. The Exchange Stock Index for the next day is considered as the target variable. The results show that the hybrid model includes Adaptive Neural Fuzzy Inference System (ANFIS) and Imperialist Competitive Algorithm, is much appropriate. This model is compared with a single ANFIS model has better approximation speed and the ability to predict the sto
Mojtaba Salehi; Alireza Korde Katooli
Abstract
Credit risk interprets as the probability of obligations non-repayment by customer in due date is considered as one of causes financial institutions bankruptcy. For this purpose, data mining techniques such as neural networks, Decision Tree, Bayesian networks, Support Vector Machine is used for customer ...
Read More
Credit risk interprets as the probability of obligations non-repayment by customer in due date is considered as one of causes financial institutions bankruptcy. For this purpose, data mining techniques such as neural networks, Decision Tree, Bayesian networks, Support Vector Machine is used for customer segmentation to high-risk and low-risk groups. In this paper, we present the hybrid Imperialist Competitive optimization algorithm and neural network for increasing classification accuracy in evaluation and measurement credit risk of bank customers. The proposed method identifies the optimistic features and eliminates unnecessary features decreases problem dimension and increases classification accuracy. To validate this method, it implements on UCI dataset and also on a reality dataset of a private Iranian bank. The experimental results show this method is more satisfactory than other data mining techniques. The neural network error for the test set decreases with selection of effective features and elimination of low-impact features by the Binary Imperialist Competitive Optimization Algorithm. In addition test data error rate remains at acceptable level for other used classification methods. This article is the first use of algorithms Imperialist Competitive for credit risk assessment of bank customers.