Mehrnaz Bagheri,
Mohammad Taghipour,
- Master, Department of Industrial Engineering, ABA Institute of Higher Education, Qazvin, Iran
- Assistant Professor, Department of Industrial Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran
Abstract
‘]
Credit risk poses the most significant threat to financial and monetary institutions. Banks strive to offer loans that generate high returns while minimizing risk. Achieving this requires the ability to accurately identify and classify credit customers, both individuals and legal entities, according to their likelihood of fully meeting their obligations. This classification is done using relevant financial and non-financial criteria. The primary goal of this study is to assess the factors that influence the evaluation of bank customers’ creditworthiness through a hybrid data mining approach, thereby enhancing decision-making processes. To accomplish this, financial and qualitative data from 1,000 customer samples were sourced from the UCI University site, utilizing 24 explanatory variables. Various prediction models, including decision trees, the naïve Bayes algorithm, support vector machines (SVM), neural networks, and combinations of these techniques, were employed to predict the risk of loan default. Additionally, the factors influencing customer creditworthiness were ranked. The findings indicated that the naïve Bayes algorithm outperformed the decision tree method in predicting loan repayment risk. Furthermore, the key variables impacting customer validation were ranked using these techniques, highlighting the superior effectiveness of the naïve Bayes algorithm in guiding banks’ decisions on credit issuance.
Keywords: Credit risk, Data mining, Decision tree, Naïve Bayesian Algorithm, Support Vector Machine (SVM), Neural networks
[This article belongs to Journal of Artificial Intelligence Research & Advances (joaira)]
Mehrnaz Bagheri, Mohammad Taghipour. Evaluation of Credit Risk of Bank Customers with a Hybrid Approach of Data Mining Techniques. Journal of Artificial Intelligence Research & Advances. 2024; 11(03):-.
Mehrnaz Bagheri, Mohammad Taghipour. Evaluation of Credit Risk of Bank Customers with a Hybrid Approach of Data Mining Techniques. Journal of Artificial Intelligence Research & Advances. 2024; 11(03):-. Available from: https://journals.stmjournals.com/joaira/article=2024/view=171720
Fetching IP address…
References ‘]
- Ghadamzan Jalali A, Habibi Machiani H, Taghipour M, Moshtaghi S. Explain the relationship between intellectual capital, organizational learning and employee performance of Parsian Bank Branches in Gilan province. Educ Adm Res Q. 2020;10(2):127–42.
- Najafi S, Saati S, Tavana M. Data envelopment analysis in service quality evaluation: an empirical study. J Ind Eng Int. 2015 Sep;11:319–30.
- Blose JE, Tankersley WB, Flynn LR. Managing service quality using data envelopment analysis. Qual Manag J. 2005 Jan 1;12(2):7–22.
- Shirouyehzad H, Lotfi FH, Shahin A, Aryanezhad MB, Dabestani R. Performance evaluation of hotels by data envelopment analysis based on customers’ perception and gap analysis. International Journal of Services and Operations Management. 2012 Jan 1;12(4):447-67.
- Baghipour Sarami F, Bozorgi Amiri A, Mououdi MA, Taghipour M. Modeling of nurses’ shift work schedules according to ergonomics: A case study in Imam Sajjad (As) Hospital of Ramsar. J Ergon. 2016;4(1):1–12. doi: 10.20286/joe-04011.
- Taghipour M, Habibi MH, Amin M. The impact of working capital management on the performance of firms listed in Tehran Stock Exchange (TSE). J Multidiscip Eng Sci Technol. 2018;7(6):24–32.
- Taghipour M, Soofi Mowloodi E, Mahboobi M, Abdi J. Application of cloud computing in system management in order to control the process. Manag Int Technol Sci Publ (ITS). 2020;3(3):34–55.
- Dastyar B, Kazemnejad H, Sereshgi AA, Jabalameli MA. Using data mining techniques to develop knowledge management in organizations: A review. J Eng Proj Prod Manag. 2017 Jul 1;7(2):80.
- Akbarnezhadbaei K, Mohamadi M, Kouloubandi A, Taghipour M. Determining a model for evaluating the knowledge management system in order to improve industries with the focus on educational technology and applying data mining concepts. J Mod Thoughts Educ. 2023 Apr 27.
- Akbarnezhadbaei K, Mohammadi M, Kouloubandi A, Taghipour M. Modeling the application of knowledge management system in order to improve the technology governance in the automotive industry of Iran using the data mining environment. Educ Adm Res. 2023 May 22;14(55).
- Bel L, Allard D, Laurent JM, Cheddadi R, Bar-Hen A. CART algorithm for spatial data: Application to environmental and ecological data. Comput Stat Data Anal. 2009 Jun 15;53(8):3082-93.
- Rutkowski L, Jaworski M, Pietruczuk L, Duda P. The CART decision tree for mining data streams. Inf Sci. 2014 May 10;266:1-5.
- Salcedo‐Sanz S, Rojo‐Álvarez JL, Martínez‐Ramón M, Camps‐Valls G. Support vector machines in engineering: an overview. Wiley Interdiscip Rev Data Min Knowl Discov. 2014 May;4(3):234-67.
Journal of Artificial Intelligence Research & Advances
| Volume | 11 |
| Issue | 03 |
| Received | August 8, 2024 |
| Accepted | August 23, 2024 |
| Published | September 11, 2024 |