Designing an Optimization-Simulation Model for Credit Scoring and Loan Structuring Using a Memetic Algorithm: A Case Study of Corporate Banking Clients

نوع مقاله : مقاله علمی پژوهشی

نویسندگان

1 Ph.D. Candidate, Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.

2 Associate Prof., Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.

3 Prof., Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.

10.22059/imj.2025.370552.1008119

چکیده

Objective: This paper introduces a groundbreaking optimization-simulation model, a novel approach that promises to revolutionize credit scoring and loan optimization for banks.
Methods: The proposed approach follows a three-stage framework: data preparation, credit scoring, and optimization simulation. In the data preparation stage, corporate client data, including bank loan information and financial statements, has been collected and processed to define and calculate relevant features. The credit scoring stage involved meticulous feature selection using the correlation method, followed by the rigorous training and testing of five classification methods: logistic regression (LR), K-nearest neighbors (KNN), artificial neural network (ANN), adaptive boosting (AdaBoost), and random forest (RF). Model performance has been evaluated using accuracy, F1-score, and area under the curve (AUC) to identify the most effective classifier. In the optimization-simulation stage, the Memetic Algorithm (MA) has been utilized to optimize loan characteristics, including loan size, interest rate, and repayment period, while minimizing the rate of loan defaults. Additionally, this stage incorporated the pre-trained credit scoring model to estimate the impact of loan characteristics on default probabilities. 
Results: A case study was conducted using data from 1,000 corporate clients of Bank Tejarat. The optimization-simulation approach has successfully reduced the loan default rate from 33% to below 5%, a significant achievement that underscores its potential to mitigate banks' credit risk. This shows the effectiveness of the proposed method in reducing credit risk for banks. Additionally, the AdaBoost technique achieved the best performance among the credit assessment models.
Conclusion: The optimization-simulation approach combines determining the optimal loan specifications with the credit assessment process. This approach considers the impact of loan characteristics on the likelihood of customer default and utilizes this information to reduce banks' credit risk

کلیدواژه‌ها

عنوان مقاله [English]

Designing an Optimization-Simulation Model for Credit Scoring and Loan Structuring Using a Memetic Algorithm: A Case Study of Corporate Banking Clients

نویسندگان [English]

  • Amir Khorrami 1
  • Mahmoud Dehghan Nayeri 2
  • Ali Rajabzadeh 3
1 Ph.D. Candidate, Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.
2 Associate Prof., Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.
3 Prof., Department of Industrial Management, Faculty of Management and Economic, Tarbiant Modares University, Tehran, Iran.
چکیده [English]

Objective: This paper introduces a groundbreaking optimization-simulation model, a novel approach that promises to revolutionize credit scoring and loan optimization for banks.
Methods: The proposed approach follows a three-stage framework: data preparation, credit scoring, and optimization simulation. In the data preparation stage, corporate client data, including bank loan information and financial statements, has been collected and processed to define and calculate relevant features. The credit scoring stage involved meticulous feature selection using the correlation method, followed by the rigorous training and testing of five classification methods: logistic regression (LR), K-nearest neighbors (KNN), artificial neural network (ANN), adaptive boosting (AdaBoost), and random forest (RF). Model performance has been evaluated using accuracy, F1-score, and area under the curve (AUC) to identify the most effective classifier. In the optimization-simulation stage, the Memetic Algorithm (MA) has been utilized to optimize loan characteristics, including loan size, interest rate, and repayment period, while minimizing the rate of loan defaults. Additionally, this stage incorporated the pre-trained credit scoring model to estimate the impact of loan characteristics on default probabilities. 
Results: A case study was conducted using data from 1,000 corporate clients of Bank Tejarat. The optimization-simulation approach has successfully reduced the loan default rate from 33% to below 5%, a significant achievement that underscores its potential to mitigate banks' credit risk. This shows the effectiveness of the proposed method in reducing credit risk for banks. Additionally, the AdaBoost technique achieved the best performance among the credit assessment models.
Conclusion: The optimization-simulation approach combines determining the optimal loan specifications with the credit assessment process. This approach considers the impact of loan characteristics on the likelihood of customer default and utilizes this information to reduce banks' credit risk

کلیدواژه‌ها [English]

  • Credit Risk
  • Credit Scoring
  • Classification
  • Memetic Algorithm
  • Optimization-Simulation Model

مراجع

Abdou, H. A., & Pointon, J. (2011). Credit scoring, statistical techniques and evaluation criteria: a review of the literature. Intelligent systems in accounting, finance and management, 18(2-3), 59-88. https://doi.org/10.1002/isaf.325
Acuna, E., & Rodriguez, C. (2004). A meta-analysis study of outlier detection methods in classification. Technical paper, Department of Mathematics, University of Puerto Rico at Mayaguez, 1, 25.
Ahmed, M. I., & Rajaleximi, P. R. (2019). An empirical study on credit scoring and credit scorecard for financial institutions. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), 8(7), 2278-1323.
Aljadani, A., Alharthi, B., Farsi, M. A., Balaha, H. M., Badawy, M., & Elhosseini, M. A. (2023). Mathematical Modeling and Analysis of Credit Scoring Using the LIME Explainer: A Comprehensive Approach. Mathematics, 11(19), 4055. https://doi.org/10.3390/math11194055
Ampountolas, A., Nyarko Nde, T., Date, P., & Constantinescu, C. (2021). A machine learning approach for micro-credit scoring. Risks, 9(3), 50. https://doi.org/10.3390/risks9030050
Baharlou, N., Aminbeydokhti, A. A., & Mohagheghnia, M. J. (2016). Comparison Between the Optimized Binary and Multinomial Logistic Regression for Credit Scoring of Real Costumers in Bank Refah Kargaran. Economics Research, 16(63), 147-166. https://doi.org/10.22054/joer.2017.7587 (in Persian)
Basu, D., Mitra, S., & Verma, N. K. (2023). Mitigating credit risk: modelling and optimizing co-insurance in loan pricing. Applied Economics, 55(29), 3422-3441. https://doi.org/10.1080/00036846.2022.2115000
Biecek, P., Chlebus, M., Gajda, J., Gosiewska, A., Kozak, A., Ogonowski, D., ... & Wojewnik, P. (2021). Enabling machine learning algorithms for credit scoring--explainable artificial intelligence (XAI) methods for clear understanding complex predictive models. arXiv preprint.      https://doi.org/10.48550/arXiv.2104.06735
Bluhm, C., Overbeck, L., & Wagner, C. (2016). Introduction to credit risk modeling. CRC Press. https://doi.org/10.1201/9781584889939
Boughaci, D., & Alkhawaldeh, A. A. (2020). Appropriate machine learning techniques for credit scoring and bankruptcy prediction in banking and finance: A comparative study. Risk and Decision Analysis, 8(1-2), 15-24. https://doi.org/10.3233/RDA-180051
Cheng, M., & Qu, Y. (2020). Does bank FinTech reduce credit risk? Evidence from China. Pacific-Basin Finance Journal, 63, 101398. https://doi.org/10.1016/j.pacfin.2020.101398
Dadmohammadi, D., & Ahmadi, A. (2017). A novel hybrid approach for training a hierarchical ensemble of neural networks for credit scoring in banking industry. Intenational Journal of Industrial Engineering and Production Management, 28(1), 161-174. (in Persian)
Daneshvar, A., Homayounfar, M., Nahavandi, B., & Salahi, F. (2021). A multi-objective approach to the problem of subset feature selection using meta-heuristic methods. Industrial Management Journal, 13(2), 278-299. https://doi.org/10.22059/imj.2021.315625.1007809 (in Persian)
Dastile, X., Celik, T., & Potsane, M. (2020). Statistical and machine learning models in credit scoring: A systematic literature survey. Applied Soft Computing, 91, 106263. https://doi.org/10.1016/j.asoc.2020.106263
Dawson, R. (2011). How significant is a boxplot outlier?. Journal of Statistics Education, 19(2). https://doi.org/10.1080/10691898.2011.11889610
Dehghan Nayeri, M., Khazaei, M., & Alinasab Imani, F. (2021). Boundary judgments analysis of the beneficiaries in banking loan allocation. Industrial Management Journal, 13(1), 27-52. https://doi.org/10.22059/imj.2021.311264.1007786 (in Persian)
Deng, X., Li, M., Deng, S., & Wang, L. (2022). Hybrid gene selection approach using XGBoost and multi-objective genetic algorithm for cancer classification. Medical & Biological Engineering & Computing, 60(3), 663-681. https://doi.org/10.1007/s11517-021-02476-x
Dželihodžić, A., Đonko, D., & Kevrić, J. (2018). Improved credit scoring model based on bagging neural network. International Journal of Information Technology & Decision Making, 17(06), 1725-1741. https://doi.org/10.1142/S0219622018500293
Eghbali, A., Razavi Hajiagha, S. H., & Amoozad, H. (2017). Performance comparison of genetic algorithm fitness function in customer credit scoring. Industrial Management Journal, 9(2), 264-245. https://doi.org/10.22059/imj.2017.226860.1007191 (in Persian)
Farbad Bayazidi, E. & Mohammadi, M. (2014). Credit rating of real customers of Bank Mellat using data mining methods. The first national congress for the development of monetary and banking management, Tehran, Iran. (in Persian)
Gambacorta, L., Huang, Y., Qiu, H., & Wang, J. (2024). How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm. Journal of Financial Stability, 101284. https://doi.org/10.1016/j.jfs.2024.101284
Ghasemnia Arabi, N., & Safaei Ghadikolaei, A. (2019). Comparison of the performances of classical models and artificial intelligence in predicting bank customers' credit status. Journal of Business Administration Researches, 10(20), 51-69. https://doi.org/10.29252/bar.2019.1320 (in Persian)
Groppelli, A. A., & Nikbakht, E. (2000). Finance, Barron's Educational Series. Inc., ISBN, 764112757.
Holland, J. H. (1973). Genetic algorithms and the optimal allocation of trials. SIAM journal on computing, 2(2), 88-105. https://doi.org/10.1137/0202009
Hosseini, S. A., & Zibaei, M. (2015). Credit risk management in agricultural bank of Mamasani using neural network model. Agricultural Economics, 9(2), 103-119. (in Persian)
Hussin Adam Khatir, A. A., & Bee, M. (2022). Machine learning models and data-balancing techniques for credit scoring: What is the best combination? Risks, 10(9), 169. https://doi.org/10.3390/risks10090169
Izadikhah, M., & Shamsi, M. (2020). Credit rating of the bank legal customers by using the improved modified Russell model (Case study: the legal customers of Arak Melli Bank). Journal of New Researches in Mathematics, 5(22), 111-126. (in Persian)
Izadikhah, M., Shamsi, M., Sheikhan, A., & Ghafouri, F. (2021). A New Hybrid Approach Based on Fitch Ranking and Data Envelopment Analysis to Evaluate the Credit Performance of the Bank's Legal Clients. Journal of Decisions & Operations Research, 6(4), 553-569. https://doi.org/10.22105/dmor.2021.250078.1225 (in Persian)
Jandaghi, G., Saranj, A., Rajaei, R., Qhasemi, A., & Tehrani, R. (2020). Evaluating credit risk based on combined model of neural network of pattern recognition and ants’ colony algorithm. Management and Development Process, 33(1), 133-170. https://doi.org/10.29252/jmdp.33.1.133 (in Persian)
Kazemi, A. Azimzadeh Tehrani, K. Abdali, A & Aryai, S (2022). Predicting the credit score of individuals using data mining algorithms (case study: customers of an Iranian state bank). Monetary and Banking Research, 48, 327-360. (in Persian)
Khorrami, A., Taghavifard, M. T., & Khatami Firouzabadi, S. M. A. (2020). Credit status assessment of bank loan applicants using CBR method. Industrial Management Studies, 18(59), 79-116. https://doi.org/10.22054/jims.2018.18574.1660 (in Persian)
Koohi, H & Gholami, R (2012). 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)
Koutanaei, F. N., Sajedi, H., & Khanbabaei, M. (2015). A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring. Journal of Retailing and Consumer Services, 27, 11-23. https://doi.org/10.1016/j.jretconser.2015.07.003
Krishna, S. J. S., Aarif, M., Bhasin, N. K., Kadyan, S., & Bala, B. K. (2024, July). Predictive Analytics in Credit Scoring: Integrating XG Boost and Neural Networks for Enhanced Financial Decision Making. In 2024 International Conference on Data Science and Network Security (ICDSNS) (pp. 1-6). IEEE. https://doi.org/10.1109/ICDSNS62112.2024.10691123
Kumar, R., & Memoria, M. (2020). A review of memetic algorithm and its application in traveling salesman problem. Int. J. Emerg. Technol., 11(2), 1110-1115.
Laborda, J., & Ryoo, S. (2021). Feature selection in a credit scoring model. Mathematics, 9(7), 746. https://doi.org/10.3390/math9070746
Lenka, S. R., Bisoy, S. K., Priyadarshini, R., & Sain, M. (2022). Empirical analysis of ensemble learning for imbalanced credit scoring datasets: A systematic review. Wireless Communications and Mobile Computing, 2022. https://doi.org/10.1155/2022/6584352
Louzada, F., Ara, A., & Fernandes, G. B. (2016). Classification methods applied to credit scoring: Systematic review and overall comparison. Surveys in Operations Research and Management Science, 21(2), 117-134. https://doi.org/10.1016/j.sorms.2016.10.001
Maleki, A., Zare, A., NiKoumaram, H., & Shahverdiani, S. (2020). Presenting an optimal credit risk model for crowdfunding process using multilayer perceptron (MLP) neural network. Financial Engineering and Portfolio Management, 11(43), 271-290. (in Persian)
Malik, M., & Thomas, L. C. (2010). Modelling credit risk of portfolio of consumer loans. Journal of the Operational Research Society, 61(3), 411-420. https://doi.org/10.1057/jors.2009.123
Markov, A., Seleznyova, Z., & Lapshin, V. (2022). Credit scoring methods: Latest trends and points to consider. The Journal of Finance and Data Science. https://doi.org/10.1016/j.jfds.2022.07.002
Mehrara, M., Mousaei, M., Tasavori, M. & Hassanzadeh, A. (2009). Credit rating of corporate clients of Parsian bank. Economic Modeling, 3(10), 121-150. (in Persian)
Metawa, N., Elhoseny, M., Hassan, M. K., & Hassanien, A. E. (2016, December). Loan portfolio optimization using genetic algorithm: a case of credit constraints. In 2016 12th international computer engineering conference (ICENCO) (pp. 59-64). IEEE. https://doi.org/10.1109/ICENCO.2016.7856446
Metawa, N., Hassan, M. K., & Elhoseny, M. (2017). Genetic algorithm based model for optimizing bank lending decisions. Expert Systems with Applications, 80, 75-82. https://doi.org/10.1016/j.eswa.2017.03.021
Mir, M., Rafiee, H., Ensan, E., Shakeri Bostanabad, R., & Yazdanpanah, R. (2022). Ranking of factors affecting credit risk of agricultural facilities: A case study of fattening units in Ardabil province of Iran. Agricultural Economics and Development, 30(3), 35-70. https://doi.org/10.30490/aead.2023.353565.1306 (in Persian)
Moradi, S., Mokhatab Rafiei, F. & Saghayi, A. (2022). Identification of dynamic patterns of credit risk of individual customers of banks and dinancial institutions (case study: three Iranian banks). Monetary and Banking Research, 15(51), 121-154. (in Persian)
Moscato, P. (1989). On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms. Caltech concurrent computation program, C3P Report, 826(1989), 37.
Munkhdalai, L., Munkhdalai, T., Namsrai, O. E., Lee, J. Y., & Ryu, K. H. (2019). An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability, 11(3), 699. https://doi.org/10.3390/su11030699
Mushava, J., & Murray, M. (2024). Flexible loss functions for binary classification in gradient-boosted decision trees: An application to credit scoring. Expert Systems with Applications, 238, 121876. https://doi.org/10.1016/j.eswa.2023.121876
Najibi, M & Mokhatab Rafiei, F. (2017). Credit rating of bank customers using clustering with a performance comparison approach of three algorithms: Kohonen, K-Means, and Two-Step. The 7th International Conference on Management and Accounting, Tehran, Iran. (in Persian)
Nalić, J., & Martinovic, G. (2020). Building a credit scoring model based on data mining approaches. International Journal of Software Engineering and Knowledge Engineering, 30(02), 147-169. https://doi.org/10.1142/S0218194020500072
Nehrebecka, N. (2018). Predicting the default risk of companies. Comparison of credit scoring models: LOGIT vs Support Vector Machines. Econometrics. Ekonometria. Advances in Applied Data Analytics, 22(2), 54-73. https://doi.org/10.15611/eada.2018.2.05
Neri, F., & Cotta, C. (2012). Memetic algorithms and memetic computing optimization: A literature review. Swarm and Evolutionary Computation, 2, 1-14. https://doi.org/10.1016/j.swevo.2011.11.003
Nili, M. & Sabzevari, H. (2008). Estimation and comparison of logit credit rating model with analytic hierarchy process (AHP) method. Industrial Engineering & Management, 24(43), 105-117. (in Persian)
Parvizian, K., Zakawt, S. M & Mohammadian, M (2009). Internal ranking of bank customers using logit regression models. Economic Research, 6, 61-89. (in Persian)
Pławiak, P., Abdar, M., Pławiak, J., Makarenkov, V., & Acharya, U. R. (2020). DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring. Information Sciences, 516, 401-418. https://doi.org/10.1016/j.ins.2019.12.045
Qadi, A., Trocan, M., Diaz-Rodriguez, N., & Frossard, T. (2023). Feature contribution alignment with expert knowledge for artificial intelligence credit scoring. Signal, Image and Video Processing, 17(2), 427-434. https://doi.org/10.1007/s11760-022-02239-7
Rastegar, M. A., & Eidi Goosh, M. (2020). Credit risk modeling: spline based logistic regression survival approach. Journal of Investment Knowledge, 9(34), 167-184. (in Persian)
Rofik, R., Aulia, R., Musaadah, K., Ardyani, S. S. F., & Hakim, A. A. (2024). The Optimization of Credit Scoring Model Using Stacking Ensemble Learning and Oversampling Techniques. Journal of Information System Exploration and Research, 2(1), 11-20.        https://doi.org/10.52465/joiser.v2i1.203
Rong, Y., Liu, S., Yan, S., Huang, W. W., & Chen, Y. (2023). Proposing a new loan recommendation framework for loan allocation strategies in online P2P lending. Industrial Management & Data Systems, 123(3), 910-930. https://doi.org/10.1108/IMDS-07-2022-0399
Runchi, Z., Liguo, X., & Qin, W. (2023). An ensemble credit scoring model based on logistic regression with heterogeneous balancing and weighting effects. Expert Systems with Applications, 212, 118732. https://doi.org/10.1016/j.eswa.2022.118732
Soltani, A., Ehtsham Rathi, R., & Abedi, S. (2023). Providing a multi-objective mathematical model for optimizing the equipment and allocation of financial resources of the banking system. Journal of Industrial Management, 15(2), 272-298. https://doi.org/10.22059/IMJ.2023.352863.1008011 (in Persian)
Sörensen, K., & Sevaux, M. (2006). MA| PM: memetic algorithms with population management. Computers & Operations Research, 33(5), 1214-1225. https://doi.org/10.1016/j.cor.2004.09.011
Soui, M., Gasmi, I., Smiti, S., & Ghédira, K. (2019). Rule-based credit risk assessment model using multi-objective evolutionary algorithms. Expert systems with applications, 126, 144-157. https://doi.org/10.1016/j.eswa.2019.01.078
Sum, R. M., Ismail, W., Abdullah, Z. H., & Shah, N. F. M. N. (2022). A New Efficient Credit Scoring Model for Personal Loan Using Data Mining Technique for Sustainability Management. Journal of Sustainability Science and Management. http://doi.org/10.46754/jssm.2022.05.005
Taghvi, M., Lotfi, A. & Sohrabi, A (2008). Credit risk model and rating of legal customers of Keshavarzi Bank. Economic Research, 4, 99-128. (in Persian)
Talaat, F. M., Aljadani, A., Badawy, M., & Elhosseini, M. (2024). Toward interpretable credit scoring: integrating explainable artificial intelligence with deep learning for credit card default prediction. Neural Computing and Applications, 36(9), 4847-4865. https://doi.org/10.1007/s00521-023-09232-2
Thomas, L., Crook, J., & Edelman, D. (2017). Credit scoring and its applications. Society for industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611974560
Tripathi, D., Edla, D. R., Bablani, A., Shukla, A. K., & Reddy, B. R. (2021). Experimental analysis of machine learning methods for credit score classification. Progress in Artificial Intelligence, 10, 217-243. https://doi.org/10.1007/s13748-021-00238-2
Wang, S. (2021). Research on optimization model of bank credit strategy. Financial Engineering and Risk Management, 4(3), 58-62. https://doi.org/10.23977/ferm.2021.040310
Witzany, J., & Witzany, J. (2017). Credit risk management. Springer International Publishing. https://doi.org/10.1007/978-3-319-49800-3
Xiao, J., Zhong, Y., Jia, Y., Wang, Y., Li, R., Jiang, X., & Wang, S. (2024). A novel deep ensemble model for imbalanced credit scoring in internet finance. International Journal of Forecasting, 40(1), 348-372. https://doi.org/10.1016/j.ijforecast.2023.03.004
Yan, B., Liang, M., & Liu, L. (2024). Optimal decisions of retailer's loans from bank. International Journal of Finance & Economics, 1-8. https://doi.org/10.1002/ijfe.2979
Yang, F., Qiao, Y., Huang, C., Wang, S., & Wang, X. (2021). An automatic credit scoring strategy (ACSS) using memetic evolutionary algorithm and neural architecture search. Applied Soft Computing, 113, 107871. https://doi.org/10.1016/j.asoc.2021.107871
Zhou, M. (2022). Credit Risk Assessment Modeling Method Based on Fuzzy Integral and SVM. Mobile Information Systems, 2022. https://doi.org/10.1155/2022/3950210
 
مدیریت صنعتی
دوره 17، شماره 2
1404
صفحه 57-27

فایل ها

هم رسانی

ارجاع به این مقاله

آمار