Validation Indicator Identification and Customer Ranking in Microloans: A Study at Middle East Bank in Iran

Document Type : Research Paper

Authors

1 Ph.D. Candidate, Department of Economic Sciences, Qeshm Branch, Islamic Azad University, Qeshm, Iran.

2 Assistant Prof., Department of Financial Management, Qeshm Branch, Islamic Azad University, Qeshm, Iran.

3 Associate Prof., Department of Accounting and Financial Management, Bandar Abbas Branch, Islamic Azad University, Bandar Abbas, Iran.

4 Associate Prof., Department of Business Management, Islamshahr Branch, Islamic Azad University, Tehran, Iran.

Abstract

Objective
In banking, customer management and validation are crucial to maintain financial security and organizational stability. A fundamental challenge in this area is the identification of appropriate indicators for validating and ranking customers. Because these customers generally have limited access to financial and credit information and cannot provide guarantors or good credit records, it is very challenging to determine correct and reliable indicators. Also, to score customers, there is a need to determine an appropriate and fair scoring system. This system should be able to place customers in different categories by considering credit and behavioral criteria and assigning them appropriate points based on their performance. In addition, there is a need to develop methods for evaluating and monitoring customers over time. This research aims to identify the indicators of validation and ranking of customers in micro-lending in Iran’s Middle East Bank.
 
Methods
This research is applied-contextual in terms of purpose and exploratory in terms of method. The statistical population of this research includes all retail banking clients of Digital Middle East Bank who seek low-interest loans at an annual rate of 2%, with a penalty rate of 6%. Statistical methods in this study were carried out in two phases: descriptive and inferential statistics. In the descriptive statistics section, various personality factors including age, gender, education, occupation, current debt status within the banking system, bounced checks history, money laundering records, bank account balance, transaction history, geographic location (residence and workplace), mobile phone model and operating system, as well as credit rating obtained from Iran's credit rating consulting company, were analyzed and presented using tables and graphs. Naive Bayes, Meta, Attribute Selected Classifier, and j48 algorithms were implemented and WEKA software was used to classify criteria and create patterns. Also, to evaluate the validation model and ranking of customers of unsupported microlending, the T-test was used at the significance level of 0.25.
 
Results
The findings indicate that when assessing a loan application, the following indicators should be considered to determine the applicant's ability to repay the loan or provide suitable collateral. Applicants demonstrating most or all of the following indicators are more likely to meet loan repayment requirements or offer adequate collateral: First, the person's previous loans have been settled 30 days and 60 days after the loan maturity date in the granting bank. Second, the person's previous loans have been settled in other banks. Third, the higher the requested loan amount, the better. Fourth, the person's age is above middle age. Fifth, the person's degree is not a bachelor's degree, diploma, or sub-diploma. Sixth, the person's score is above 40. Seventh, the operating system of the person's phone is not Android. Eighth, the person's phone model is not SAMSUNG or XIAOMI. Ninth, if the investigations related to the person's money laundering status are negative, then preferably, and if necessary, the loan of that person can be approved.
 
Conclusion
In this approach (unsupported micro-lending), banks should extend loans to individuals only after acquiring comprehensive knowledge about them before initiating any new credit arrangement. It is vital to gather the required data and ensure their creditworthiness and positive reputation. Banks need to obtain reliable and detailed information about borrowers, as extending facilities for maximum profitability also exposes the bank to associated risks.

Keywords

Main Subjects

References

 
Arabi, S H. & Shah Jamali, M. (2018). Ranking of credit risk management tools in interest-free banking using AHP technique. Journal of Islamic Economics and Banking, 8 (28), 7-39. (in Persian)
Beikzadeh, J., Aghazadeh, G. & Aghazadeh, M. (2013). Investigating factors affecting credit risk and prioritizing credit scoring criteria (6C) of bank customers using AHP technique: a case study of National Bank of West Azarbaijan province. Trend (Economic Research Trends), 21(68), 121-150. (in Persian)
Hadavi, M H ., Ghasemi, B. & Sarmad Saidi, S. (2023). Designing a pattern for prioritizing rial letter of credit applicants: a strategy for developing credit services in Saderat Bank of Iran. Financial monetary economy, 30(26). (in Persian)
Hota, L. (2023). A Comparative Performance Assessment for Prediction of Loan Approval in Financial Sector. Mathematics, 8(10), 1756.
Idrees, A. M., Elseddawy, A. I. & Zeidan, M. O. (2019). Knowledge discovery based framework for enhancing the house of quality. International Journal of Advanced Computer Science and Applications, 10(7), 324-331.
Kohi, H. & Gholami, R. (2011). Credit rating of legal clients of the industry sector using data envelopment analysis (DEA) model. Quantitative Studies in Management, 3(3), 115-138. (in Persian)
Li, X., & Sun, Y. (2021). Application of RBF neural network optimal segmentation algorithm in credit rating. Neural Computing and Applications, 33(14), 8227-8235.
Mahdavi, K. & Horri, M. (2014). Model for Credit Rating Prediction of Banks CustomersBy use of A Meta-Heuristic Hybrid Multi-Attribute Fuzzy neural network-Ant Colony (Case study on Tehran's Postbank branches). Management Research in Iran, 19(1), 91-116.
(in Persian)
Mohabi, S., Fadainejad, M. I. & Usulian, M. (2022). Prediction of total index of Tehran Stock Exchange using support vector regression based on dimensionality reduction technique. Financial Management Strategy, 10(38), 1-26. (in Persian)
Moradi, S. & Mokhatab Rafiei, F. (2019). A dynamic credit risk assessment model with data mining techniques: evidence from Iranian banks. Financial Innovation, 5(1), 1-27.
Mun, J. H. & Jung, S. W. (2021). A customer credit Prediction Researched to Improve Credit Stability based on Artificial Intelligence. Korea Journal of Artificial Intelligence, 9(1), 21–27.
Padimi, V., Venkata, S. T. & Devarani, D. N. (2022). Applying Machine Learning Techniques To Maximize The Performance of Loan Default Prediction. Journal of Neutrosophic and Fuzzy Systems (JNFS), 2(2), 44-56.‏
Rahmani, P. & Mohammadi Khanqah, G. (2023). Credit rating and cost of capital. Financial Research, 25 (1), 126-110. (in Persian)
Rai, R., Ansari, H. E. & Portalebi Jaghargh, M. (2017). Investigating the effects of market power and income structure on profitability and bankruptcy risk in Iran's banking system. Financial Management Strategy, 6(2), 51-72. (in Persian)
Raisi, S., Bajlan, S. & Falahpour, S. (2024). Optimization of credit portfolio of banks using actuarial approach and artificial neural network. Financial research. doi: 10.22059/FRJ.2021.311064.1007074 (in Persian)
Saha, S. & Waheed, S. (2017). Credit Risk of Bank Customers can be Predicted from Customer's Attribute using Neural Network. International Journal of Computer Applications, 161(3), 39-43.
Sarkanian, J., Rai, R., Shirkund, S. & Abbasian, E. (2023). Evaluating the effect of bank characteristics on banks' lending channel with the FAVAR approach. Financial Research, 25 (1), 1-25. (in Persian)
Sha, Y. (2022). Rating manipulation and creditworthiness for platform economy: Evidence from peer-to-peer lending. International Review of Financial Analysis, 84, 102393.‏
Sharafi, G., Fathi Hafashjani, K. & Ahmadi, F. (2023). Identification of Factors Affecting Project Financing Risk. Financial Research Journal, 25(3), 485-507.
Soltani, S. (2021). Validation of customers of financial institutions using artificial neural network developed with the help of genetic algorithm (case study: National Bank of Ilam). Quarterly Journal of New Approaches in Basic Science, Technical and Engineering Research, 4(13), 42-61. (in Persian)
Sundar, R., Sapna, S. & Mohit, G. (2021). Impact of Pre Loan assessment customer credit worthiness on loan defaults at later stages in Rural Segment – a study at Vehicle Financing NBFC. Turkish Journal of Computer and Mathematics Education, 12(12), 232-240.
Wang, Y., Jia, Y., Fan, S. & Xiao, J. (2023). Deep Reinforcement Learning Based on Balanced Stratified Prioritized Experience Replay for Customer Credit Scoring in Peer-to-Peer Lending.‏ Artificial Intelligence Review, 57(4).
Xia, Y., Guo, X., Li, Y., He, L. & Chen, X. (2022). Deep learning meets decision trees: An application of a heterogeneous deep forest approach in credit scoring for online consumer lending. Journal of Forecasting, 41(8), 1669-1690.‏
Xiaobing, H., Xiaobing, L. & Yuanqian, R. (2018). Enterprise credit risk evaluation based on neural network algorithm. Cognitive Systems Research, 52, 317-324.
Financial Research Journal
Volume 26, Issue 2
2024
Pages 399-423

Files

Share

How to cite

Statistics