A model for validating bank customers using multilayer perceptron neural network and imperialist competitive algorithm (ICA)

Masomian, Bahman; Mirhosseini, Seyed Mohsen

doi:10.22075/ijnaa.2023.31084.4561

A model for validating bank customers using multilayer perceptron neural network and imperialist competitive algorithm (ICA)

Document Type : Research Paper

Authors

Bahman Masomian ¹

Seyed Mohsen Mirhosseini ²

¹ Department of Computer Engineering, Hi.C, Islamic Azad University, Hidaj, Iran

² Department of Computer Engineering, Ka. C, Islamic Azad University, Karaj, Iran

10.22075/ijnaa.2023.31084.4561

Abstract

Given the highly competitive nature of the banking industry, financial and credit institutions continually seek to identify the most reliable and profitable customers. They are particularly concerned about loan defaults or delays in repayment, which can negatively impact economic growth. Credit scoring models are among the most effective tools in modern banking for evaluating customer creditworthiness. These models enable banks to assess credit requests with greater accuracy and lower cost. In recent years, machine learning techniques—especially predictive classifiers-have been extensively applied to credit scoring and customer classification. This study introduces a novel hybrid model that combines a Multilayer Perceptron (MLP) neural network with the Imperialist Competitive Algorithm (ICA). In the proposed approach, ICA is employed to optimise the hyperparameters of the MLP network. The model is tested on a dataset comprising 2,571 real customers from Saderat Bank, categorised into default and non-default classes based on 11 identified features. The results demonstrate that the proposed model achieves higher accuracy and lower prediction error in assessing customers’ credit behaviour.

Keywords

Credit Risk

Credit Scoring

Probability of Default

Multilayer Perceptron Neural Network

Imperialist Competitive Algorithm

[1] M. Ala’raj and M. Abbod, Classifiers consensus system approach for credit scoring, Knowledge-Based Syst. 104 (2016), 89–105.

[2] E. Atashpaz-Gargari and C. Lucas, Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition, IEEE Cong. Evolut. Comput., 2007, pp. 4661–4667.

[3] J. Bessis, Risk Management in Banking, John Wiley & Sons, 2011.

[4] M. Faheem, AI-Driven risk assessment models: Revolutionizing credit scoring and default prediction, Iconic Res. Engin. J. 5 (2021), 177–186.

[5] T. Lee, C. Chiu, C. Lu, and I. Chen, Credit scoring using the hybrid neural discriminant technique, Expert Syst. Appl. 23 (2002), 245–254.

[6] C. Luo, D. Wu, and D. Wu, A deep learning approach for credit scoring using credit default swaps, Engin. Appl. Artific. Intell. 65 (2017), 465–470.

[7] R. Merton, On the pricing of corporate debt: The risk structure of interest rates, J. Finance 29 (1974), 449–470.

[8] G. Morton, Managing Bank Risk: An Introduction to Broad Base Credit Engineering, Academic Press, Amsterdam, 2003.

[9] V. Neagoe, A. Ciotec, and G. Cucu, Deep convolutional neural networks versus multilayer perceptron for financial prediction, Int. Conf. Commun., 2018, pp. 201–206.

[10] M. Peihani, Basel committee on banking supervision: A primer on governance, history, and legitimacy—Part i, Brill Rese. Perspect. Int. Bank. Secur. Law 1 (2016), no. 1, 1–87.

[11] M. Soui, I. Gasmi, S. Smiti, and K. Ghedira, Rule-based credit risk assessment model using multi-objective evolu[1]tionary algorithms, Expert Syst. Appl. 126 (2019), 144–157.

[12] K. Tran, T. Duong, and Q. Ho, Credit scoring model: A combination of genetic programming and deep learning, Future Technol. Conf., 2016, pp. 145–149.

[13] H. Van Greuning and S. Bratanovic, Analyzing Banking Risk: A Framework for Assessing Corporate Governance and Risk Management, World Bank Publications, 2020.

[14] M. Vazan, Machine Learning and Data Science: Foundations, Concepts, Algorithms, and Tools, Miaad Andisheh Pub., 2021. [In Persian]

[15] B. Zhu, W. Yang, H. Wang, and Y. Yuan, A hybrid deep learning model for consumer credit scoring, Int. Conf. Artific. Intell. Big Data, 2018, pp. 205–208.