Clustering of Iranian Bank Customers using Fuzzy logic and LSTM linear regression model

Abstract

Identifying and evaluating customers today is a multi-million-dollar business worldwide, and its financial volume is increasing daily. In recent years, new technologies have opened up many ways for banks to provide more opportunities to evaluate their customers. Identifies and analyzes the different techniques of behavior performed in a bank, somehow identifying the behavior of users or customers trying to predict their future behavior and reducing the risk of facility allocation. The proposed method has been evaluated with standard Bank of Iran Banking system data, and the features extracted by the fuzzy classifier and LSTM linear regression model are used. The results of this classifier on the properties extracted by the proposed algorithm are compared with the results of the classification using all the features. Removing features is done by the rapper method to minimize the number of suitable features. According to studies, the accuracy has been around 91.23% for first-class customers, which is good precision.

Keywords

• Fuzzy logic
• LSTM method
• clustering
• pre-process

References

1. [1] T. Samaricheva, L. Yuzkov and a. A. Shpuhanych, "Evaluation of the Efficiency of the Bank's Loan Portfolio Management: Theory and Practice," Business Navigator, vol. 1, no. 68, pp. 126-131, 2022.
2. [2] M. Qulmetov, "Improving Lending Mechanisms, Taking into Account the Minimization of Risks," Economics and Education, vol. 24, no. 3, pp. 132-139, 2023.
3. [3] S. A. Amirsadat and a. S. J. Iranban, "Designing Credit Analysis Model of Bank Customers using Adaptive Neural Fuzzy Reasoning System," Spectrum, vol. 4, no. 2, 2015.
4. [4] N. Shtefan, "Bank's Credit and Investment Portfolio Structure Optimization," Economic Bulletin of Dnipro University of Technology, no. 4, pp. 145-156, 2021.
5. [5] M. Tang, W. Zeng and R. Zhao, "Improving the Efficiency of Customer’s Credit Rating," BCP Business & Management , vol. 48, pp. 33-42, 2023.
6. [6] O. Komlichenko and a. N. Rotan, "Loan Portfolio Structure Model and Its Impact on the Bank's Efficiency," Odessa National University Herald. Economy, vol. 3, no. 88, pp. 103-110, 2021.
7. [7] V. Fursa, D. Korobtsova and a. H. Tolkachova, "Optimization of Company Financial Management Strategies," Actual problems of innovative economy and law, pp. 54-58.
8. [8] L. Yu, S. Wang and a. K. K. Lai, "Credit risk assessment with a multistage neural network ensemble learning approach," Expert systems with applications, vol. 34, no. 2, pp. 1434-1444, 2008.

9. [9] H. Zhang, Z. Guo and a. Y. Sun, "Analysis of Bank Customer Default Risk Based on Embedded Microprocessor Wireless Communication," Security and Communication Networks, pp. 1-11, 2022.
10. [10] Q. Wu, "Real-time Predictive Analysis of Loan Risk with Intelligent Monitoring and Machine Learning Technique," in Presented at the 2022 IEEE 4th International Conference on Power, henyang, China, 2022.
11. [11] E. Oseni, "Assessment of the Five Cs of Credit in the Lending Requirements of the Nigerian Commercial Banks," International Journal of Economics and Financial Issues, vol. 13, no. 4, pp. 58-65, 2023.
12. [12] I. D. C. Arifah and a. I. U. Nihaya, "Artificial Intelligence in Credit Risk Management of Peer-to-Peer Lending Financial Technology: Systematic Literature Review," in In 2023 6th International Conference of Computer and Informatics Engineering, Lombok, Indonesia, 2023.
13. [13] Y. Song, X. Y. Yuyan Wang, D. Wang, Y. Yin and a. Y. Wang, "Multi-view ensemble learning based on distance-to-model and adaptive clustering for imbalanced credit risk assessment in P2P lending," Information Sciences, vol. 525, pp. 182-204, 2020.
14. [14] J. Nayak, B. Naik and a. H. Behera, "Fuzzy C-means (FCM) clustering algorithm: a decade review from 2000 to 2014," in In Computational Intelligence in Data Mining: Proceedings of the International Conference on CIDM, 20-21 December 201, Springer India, 2015.
15. [15] A. Mukhopadhyay, U. Maulik, S. Bandyopadhyay and a. C. A. C. Coello, "Survey of multiobjective evolutionary algorithms for data mining: Part II.," IEEE Transactions on Evolutionary Computation, vol. 18, no. 1, pp. 20-35, 2013.
16. [16] M. Wang and a. H. Ku, "Utilizing historical data for corporate credit rating assessment," Expert Systems with Applications 165, vol. 165, no. 113925, pp. 1-12, 2021.
17. [17] G. Dong, K. K. Lai and a. J. Yen, "Credit scorecard based on logistic regression with random coefficients," Procedia Computer Science, vol. 1, no. 1, pp. 2463-2468, 2010.
18. [18] G. Wang, J. Hao, J. Ma and a. H. Jiang, "A comparative assessment of ensemble learning for credit scoring," Expert systems with applications, vol. 38, no. 1, pp. 23-230, 2011.
19. [19] N. Arora, D. A. GAUR and a. M. Babita, "credit appraisal process of SBI: A case study of branch of SBI in hisar," Arth prabhand: A journal of economics and management , vol. 2, pp. 10-26, 2013.
20. [20] H. Shakerian, H. D. Dehnavi and a. S. B. Ghanad, "The implementation of the hybrid model SWOT-TOPSIS by fuzzy approach to evaluate and rank the human resources and business strategies in organizations (case study: road and urban development organization in Yazd)," Procedia-Social and Behavioral Sciences , vol. 230, pp. 307-316, 2016.
21. [21] L. Ferreira, D. Borenstein and a. E. Santi, "Hybrid fuzzy MADM ranking procedure for better alternative discrimination," Engineering Applications of Artificial Intelligence 50, vol. 50, pp. 71-82, 2016.
22. [22] S. B. S. Taneja, S. Gupta, H. Narwal, A. Jain and a. A. Kathuria, "A fuzzy logic based approach for data classification," in In Data Engineering and Intelligent Computing: Proceedings of IC3T , Singapore, 2016.
23. [23] J. Zheng, H. Cui, X. Li, L. Meng and a. T. Wang, "The clustering for clients in a bank based on big data," in In 2018 4th International Conference on Universal Village (UV), Boston, MA, USA, 2018.
24. [24] L. Hu, X. Pan, Z. Tang and a. X. Luo, "A fast fuzzy clustering algorithm for complex networks via a generalized momentum method," IEEE Transactions on Fuzzy Systems, vol. 30, no. 9, pp. 3473-3485, 2021.
25. [25] S. Balovsyak, O. Derevyanchuk, H. Kravchenko, Y. Ushenko and Z. and Hu, "Clustering Students According to their Academic Achievement Using Fuzzy Logic," Clustering Students According to their Academic Achievement Using Fuzzy Logic, vol. 6, pp. 31-43, 2023.
26. [26] W. Fan and a. A. Bifet, "Mining big data: current status, and forecast to the future," ACM SIGKDD explorations newsletter, vol. 14, no. 2, pp. 1-5, 2013.
27. [27] T. Velmurugan, "Performance based analysis between k-Means and Fuzzy C-Means clustering algorithms for connection oriented telecommunication data," Applied Soft Computing, vol. 19, pp. 134-146, 2014.
28. [28] A. Mukhopadhyay, U. Mauli, S. Bandyopadhyay and a. C. A. C. Coello, "A survey of multiobjective evolutionary algorithms for data mining: Part I.," IEEE Transactions on Evolutionary Computation, vol. 18, no. 1, pp. 4-19, 2013.
29. [29] M. K. I. Rahmani, N. Pal and a. K. Arora, "Clustering of image data using K-means and fuzzy K-means," International Journal of Advanced Computer Science and Applications, vol. 5, no. 7, 2014.
30. [30] T.-P. Hong, Y.-C. Lee and a. M.-T. Wu, "An effective parallel approach for genetic-fuzzy data mining," Expert Systems with Applications, vol. 41, no. 2, pp. 655-662, 2014.
31. [31] T. Singh and a. M. Mahajan, "Performance comparison of fuzzy C means with respect to other clustering algorithm," International journal of advanced research in computer science and software engineering, vol. 4, no. 5, pp. 89-93, 2014.