A framework for integrating transfer learning and crowd intelligence to overcome the data-poor regime in emerging businesses

Nooraei Abadeh, Maryam; Ajoudanian, Shohreh; Bahadori, Sondos

doi:10.22054/ims.2026.87652.2661

Document Type : Research Paper

Authors

¹ Department of Computer Engineering, Abadan Branch, Islamic Azad University, Abadan, Iran

² Department of Computer Engineering, Na.C., Islamic Azad University, Najafabad, Iran,

³ Department of Computer Engineering, Arv. C., Islamic Azad University, Abadan, Iran

https://doi.org/10.22054/ims.2026.87652.2661

Abstract

Early-stage startups face the problem of cold start, as they have limited real-world data to train AI models. This lack of data, combined with the incompatibility of generic data with specific business needs, reduces the accuracy of predictions and recommendations. Rapid changes in data and concepts (such as data and concept drift), the risk of forgetting prior knowledge in transfer learning, and the heterogeneous quality of user feedback are the main challenges in this area. The proposed framework is an integrated and scalable architecture that combines transfer learning and crowd intelligence. The framework consists of four parts: collection and preprocessing of (limited), generic, and user feedback real-world data; transfer learning with a pretrained model and efficient optimization to prevent forgetting prior knowledge; model enhancement with filtered and weighted user feedback; and continuous prediction by monitoring data and concept changes with mathematical criteria. The training data is composed of a combination of real, generic, and user feedback data, and optimization is performed by minimizing error and controlling complexity. Evaluation on three real datasets. Other metrics such as prediction accuracy, positive sample detection, balance between the two, error reduction, and data stability were also improved in all three datasets, especially in investment data that is more scattered. This framework increases the efficiency of limited data and ensures the stability of the model.

Keywords

Main Subjects

Management approaches in the field of smart

References

Adewale, T. (2024). "Transfer Learning Applications in Cross-Market Investment Strategies."

Ali, W., X. Zhou and J. Shao (2025). "Privacy-preserved and responsible recommenders: From conventional defense to federated learning and blockchain." ACM Computing Surveys 57(5): 1-35. https://doi.org/10.1145/3708982.

Alzubaidi, L., M. A. Fadhel, O. Al-Shamma, J. Zhang, J. Santamaría, Y. Duan and S. R. Oleiwi (2020). "Towards a better understanding of transfer learning for medical imaging: a case study." Applied Sciences 10(13): 4523. https://doi.org/10.3390/app10134523.

Da, Z. and X. Huang (2020). "Harnessing the wisdom of crowds." Management Science 66(5): 1847-1867. https://doi.org/10.1287/mnsc.2019.3294.

Fayaz-Bakhsh, M., D. Ataee and M. Fazli (2025). "Cold Start Active Preference Learning in Socio-Economic Domains." arXiv preprint arXiv: https://doi.org/10.48550/arXiv.2508.05090.

Frikha, A. (2022). Deep knowledge transfer for generalization across tasks and domains under data scarcity, lmu. https://doi.org/10.5282/edoc.30833.

Gunasekaran, S. S., S. A. Mostafa and M. S. Ahmad (2015). Knowledge transfer model in collective intelligence theory. Advances in Intelligent Informatics, Springer: 481-491.

Hedderich, M. A., L. Lange, H. Adel, J. Strötgen and D. Klakow (2020). "A survey on recent approaches for natural language processing in low-resource scenarios.". https://doi.org/10.48550/arXiv.2010.12309.

Huang, Y.-C. and Y.-C. Chin (2018). "Transforming collective knowledge into team intelligence: the role of collective teaching." Journal of Knowledge Management 22(6): 1243-1263. https://doi.org/10.1108/JKM-03-2018-0186.

Irshad, M. S., Q. Xin and H. Arshad (2018). "Competitiveness of Pakistani rice in international market and export potential with global world: A panel gravity approach." Cogent Economics & Finance 6(1): 1486690. https://doi.org/10.1080/23322039.2018.1486690.

Jafri, S. I. H., R. Ghazali, I. Javid, Z. Mahmood and A. A. A. Hassan (2022). "Deep transfer learning with multimodal embedding to tackle cold-start and sparsity issues in recommendation system." Plos one 17(8): e0273486. https://doi.org/10.1371/journal.pone.0273486.

Jeon, H. J., S. Liu, Y. Li, J. Lyu, H. Song, J. Liu, P. Wu and Z. Zhu (2024). "Epinet for Content Cold Start." arXiv preprint arXiv:2412.04484. https://doi.org/10.48550/arXiv.2412.04484.

Kairouz, P., H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode and R. Cummings (2021). "Advances and open problems in federated learning." Foundations and trends® in machine learning 14(1–2): 1-210. https://doi.org/10.1561/2200000083.

Kamar, E., S. Hacker and E. Horvitz (2012). Combining human and machine intelligence in large-scale crowdsourcing. Aamas. https://doi.org/10.5555/2343576.2343643.

Kazai, G., J. Kamps and N. Milic-Frayling (2013). "An analysis of human factors and label accuracy in crowdsourcing relevance judgments." Information retrieval 16(2): 138-178. https://doi.org/10.1007/s10791-012-9205-0.

Lam, X. N., T. Vu, T. D. Le and A. D. Duong (2008). Addressing cold-start problem in recommendation systems. Proceedings of the 2nd international conference on Ubiquitous information management and communication. https://doi.org/10.1145/1352793.1352837.

Lao, D., X. Yang, Q. Wu and J. Yan (2022). Variational inference for training graph neural networks in low-data regime through joint structure-label estimation. Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining. https://doi.org/10.1145/3534678.3539283.

Li, S., S. A. Mohd Noah and Y. Xu "Drn-Cskt: Solving Cold-Start in Knowledge Tracing with Disentangled Attention and Retentive Networks."

Nerurkar, I. M. K. C. B. (2025). "The Role of Transfer Learning in Low-Data Regimes: Applications and Challenges."

Pan, S. J. and Q. Yang (2009). "A survey on transfer learning." IEEE Transactions on knowledge and data engineering 22(10): 1345-1359. https://doi.org/10.1109/TKDE.2009.191.

Paschek, D., C. T. Luminosu and A. Draghici (2017). Automated business process management–in times of digital transformation using machine learning or artificial intelligence. MATEC web of conferences, EDP Sciences. https://doi.org/10.1051/matecconf/201712104007.

Pham, H., Z. Dai, G. Ghiasi, K. Kawaguchi, H. Liu, A. W. Yu, J. Yu, Y.-T. Chen, M.-T. Luong and Y. Wu (2023). "Combined scaling for zero-shot transfer learning." Neurocomputing 555: 126658. https://doi.org/10.1016/j.neucom.2023.126658.

Wang, K.-J., L. Juni Asrini, L. Sanjaya and H.-P. Nguyen (2022). "Model for deep learning-based skill transfer in an assembly process." Advanced Engineering Informatics 52: 101643. https://doi.org/10.1016/j.aei.2022.101643.

Woolley, A., C. Chabris, A. Pentland, N. Hashmi and T. Malone (2010). "Evidence of a Collective Intelligence Factor in the Performance of Human Groups." Science (New York, N.Y.) 330: 686-688. https://doi.org/10.1126/science.1193147.

Xie, J., Y. Lu, S.-C. Zhu and Y. Wu (2016). A theory of generative convnet. International conference on machine learning, PMLR. https://doi.org/10.48550/arXiv.1602.03264.

Yu, Y., R. Zhang, R. Xu, J. Zhang, J. Shen and C. Zhang (2022). "Cold-start data selection for few-shot language model fine-tuning: A prompt-based uncertainty propagation approach." arXiv preprint arXiv:2209.06995. https://doi.org/10.48550/arXiv.2209.06995.

Business Intelligence Management Studies

A framework for integrating transfer learning and crowd intelligence to overcome the data-poor regime in emerging businesses

References

References

Volume 15, Issue 55
May 2026
Pages 337-374

A framework for integrating transfer learning and crowd intelligence to overcome the data-poor regime in emerging businesses

References

References

Volume 15, Issue 55May 2026Pages 337-374

Volume 15, Issue 55
May 2026
Pages 337-374