A Comparative Study of Loan Approval Prediction Using Machine Learning Methods

Abstract

Loan prediction plays an important role in the process of evaluating loan applications by financial institutions. Machine learning models can automate this process and make the lending process faster and more efficient. In this context, the main objective of this research is to develop models for loan approval prediction using machine learning algorithms such as Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, and Random Forest and to compare their performances. In addition, determining the effect of K-Best and Recursive Feature Elimination feature selection methods on model performances is another important objective of the research. Furthermore, the evaluation of the effectiveness of techniques such as cross-validation (K-Fold) and Train, Test and Validation in measuring the performance of models is also among the objectives of the research. The findings revealed that married individuals are more likely to be approved for loans than single individuals, high income individuals more likely than low-income individuals, males more likely than females, and university graduates more likely than non-university graduates. According to the performance measures, Random Forest was the most successful algorithm with an accuracy rate of 97.71% in loan approval prediction. To achieve this accuracy rate, feature selection was performed with the Recursive Feature Elimination method and the measurement was made with the cross-validation method. It was found that the feature selection methods have a significant impact on the model performances and the Recursive Feature Elimination method was the most successful method. Moreover, the highest accuracy rate achieved by the Random Forest algorithm, which showed the highest performance in all cases, was measured by cross-validation.

Keywords

• Data mining
• loan prediction
• machine learning
• banking sector
• feature selection
• cross-validation

References

1. [1] B. Huang and L. C. Thomas, "Credit card pricing and impact of adverse selection," J. Oper. Res. Soc., vol. 65, no. 8, pp. 1193-1201, 2014.
2. [2] V. Leninkumar, "The relationship between customer satisfaction and customer trust on customer loyalty," Int. J. Acad. Res. Bus. Soc. Sci., vol. 7, no. 4, pp. 450-465, 2017.
3. [3] M. Siles, S. D. Hanson, and L. J. Robison, "Socio‐economics and the probability of loan approval," Appl. Econ. Perspect. Policy, vol. 16, no. 3, pp. 363-372, 1994.
4. [4] J. E. Stiglitz and A. Weiss, "Incentive effects of terminations: Applications to the credit and labor markets," Am. Econ. Rev., vol. 73, no. 5, pp. 912-927, 1983.
5. [5] S. T. Bharath, S. Dahiya, A. Saunders, and A. Srinivasan, "Lending relationships and loan contract terms," Rev. Financial Stud., vol. 24, no. 4, pp. 1141-1203, 2011.
6. [6] S. M. Livingstone and P. K. Lunt, "Predicting personal debt and debt repayment: Psychological, social and economic determinants," J. Econ. Psychol., vol. 13, no. 1, pp. 111-134, 1992.
7. [7] N. W. Hillman, "College on credit: A multilevel analysis of student loan default," Rev. High. Educ., vol. 37, no. 2, pp. 169-195, 2014.
8. [8] The Banks Association of Türkiye, "Consumer Loans and Housing Loans," 2023. [Online]. Available: https://www.tbb.org.tr/Content/Upload/istatistikiraporlar/ekler/4227/Tuketici_Kredileri_Raporu-Eylul_2023.pdf

9. [9] S. Carter, E. Shaw, W. Lam, and F. Wilson, "Gender, entrepreneurship, and bank lending: The criteria and processes used by bank loan officers in assessing applications," Entrepreneurship Theory and Practice, vol. 31, no. 3, pp. 427-444, 2007.
10. [10] C. Parkan and M. L. Wu, "Measurement of the performance of an investment bank using the operational competitiveness rating procedure," Omega, vol. 27, no. 2, pp. 201-217, 1999.
11. [11] J. S. Chiou, "The antecedents of consumers’ loyalty toward Internet service providers," Inf. & Manage., vol. 41, no. 6, pp. 685-695, 2004.
12. [12] R. S. Swift, Accelerating customer relationships: Using CRM and relationship technologies. Prentice Hall Professional, 2001.
13. [13] S. Sachan, J. B. Yang, D. L. Xu, D. E. Benavides, and Y. Li, "An explainable AI decision-support-system to automate loan underwriting," Expert Syst. Appl., vol. 144, p. 113100, 2020.
14. [14] B. Lepri, N. Oliver, E. Letouzé, A. Pentland, and P. Vinck, "Fair, transparent, and accountable algorithmic decision-making processes: The premise, the proposed solutions, and the open challenges," Philos. Technol., vol. 31, pp. 611-627, 2018.
15. [15] J. F. Martínez Sánchez and G. Pérez Lechuga, "Assessment of a credit scoring system for popular bank savings and credit," Contad. y Adm., vol. 61, no. 2, pp. 391-417, 2016.
16. [16] R. Parasuraman, M. Mouloua, R. Molloy, and B. Hilburn, "Monitoring of automated systems," in Automation and human performance, CRC Press, 2018, pp. 91-115.
17. [17] M. McKay, "Best practices in automation security," in 2012 IEEE-IAS/PCA 54th Cement Industry Technical Conference, May 2012, pp. 1-15.
18. [18] D. Bertsimas, and J. Dunn, “Optimal classification trees,” Machine Learning, vol. 106, pp. 1039-1082, 2017.
19. [19] A. J. Wyner, M. Olson, J. Bleich, and D. Mease, “Explaining the success of adaboost and random forests as interpolating classifiers,” Journal of Machine Learning Research, vol. 18, no. 48, 1-33, 2017.
20. [20] Z. G. Liu, Q. Pan, and J. Dezert, “A new belief-based K-nearest neighbor classification method,” Pattern Recognition, vol. 46, no. 3, pp. 834-844, 2013.
21. [21] I. W. Tsang, J. T. Kwok, P. M. Cheung, and N. Cristianini, “Core vector machines: Fast SVM training on very large data sets,” Journal of Machine Learning Research, vol. 6, no. 4, 2005.
22. [22] J. Wu, X. Y. Chen, H. Zhang, L. D. Xiong, H. Lei, and S. H. Deng, "Hyperparameter optimization for machine learning models based on Bayesian optimization," Journal of Electronic Science and Technology, vol. 17, no. 1, pp. 26-40, 2019.
23. [23] A. Janecek, W. Gansterer, M. Demel, and G. Ecker, "On the relationship between feature selection and classification accuracy," in New challenges for feature selection in data mining and knowledge discovery, PMLR, 2008, pp. 90-105.
24. [24] E. Kadam, A. Gupta, S. Jagtap, I. Dubey, and G. Tawde, "Loan approval prediction system using logistic regression and CIBIL score," in 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), Jul. 2023, pp. 1317-1321.
25. [25] A. S. Kadam, S. R. Nikam, A. A. Aher, G. V. Shelke, and A. S. Chandgude, "Prediction for loan approval using machine learning algorithm," Int. Res. J. Eng. Technol. (IRJET), vol. 8, no. 04, pp. 4089-4092, 2021.
26. [26] P. S. Saini, A. Bhatnagar, and L. Rani, "Loan approval prediction using machine learning: A comparative analysis of classification algorithms," in 2023 3rd Int. Conf. Adv. Comput. Innov. Technol. Eng. (ICACITE), May 2023, pp. 1821-1826.
27. [27] V. Singh, A. Yadav, R. Awasthi, and G. N. Partheeban, "Prediction of modernized loan approval system based on machine learning approach," in 2021 Int. Conf. Intell. Technol. (CONIT), Jun. 2021, pp. 1-4.
28. [28] Y. Diwate, P. Rana, and P. Chavan, "Loan Approval Prediction Using Machine Learning," Int. Res. J. Eng. Technol. (IRJET), vol. 8, no. 05, 2021.
29. [29] M. Alaradi and S. Hilal, "Tree-based methods for loan approval," in 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), Oct. 2020, pp. 1-6.
30. [30] V. S. Kumar, A. Rokade, and S. MS, "Bank loan approval prediction using data mining technique," Int. Res. J. Modern. Eng. Technol. Sci., vol. 2, no. 05, pp. 965-970, 2020.
31. [31] N. Uddin, M. K. U. Ahamed, M. A. Uddin, M. M. Islam, M. A. Talukder, and S. Aryal, "An ensemble machine learning based bank loan approval predictions system with a smart application," International Journal of Cognitive Computing in Engineering, vol. 4, pp. 327-339, 2023.
32. [32] J. Tejaswini, T. M. Kavya, R. D. N. Ramya, P. S. Triveni, and V. R. Maddumala, "Accurate loan approval prediction based on machine learning approach," J. Eng. Sci., vol. 11, no. 4, pp. 523-532, 2020.
33. [33] H. V. Ramachandra, G. Balaraju, R. Divyashree, and H. Patil, "Design and simulation of loan approval prediction model using AWS platform," in 2021 Int. Conf. Emerg. Smart Comput. Informatics (ESCI), Mar. 2021, pp. 53-56.
34. [34] H. Meshref, "Predicting loan approval of bank direct marketing data using ensemble machine learning algorithms," Int. J. Circuits. Syst. Signal Process., vol. 14, pp. 914-922, 2020.
35. [35] A. Gupta, V. Pant, S. Kumar, and P. K. Bansal, "Bank Loan Prediction System using Machine Learning," in 2020 9th International Conference System Modeling and Advancement in Research Trends (SMART), Dec. 2020, pp. 423-426.
36. [36] M. A. Sheikh, A. K. Goel, and T. Kumar, "An approach for prediction of loan approval using machine learning algorithm," in 2020 Int. Conf. Electron. Sustainable Commun. Syst. (ICESC), Jul. 2020, pp. 490-494.
37. [37] P. Tumuluru, L. R. Burra, M. Loukya, S. Bhavana, H. M. H. CSaiBaba, and N. Sunanda, "Comparative Analysis of Customer Loan Approval Prediction using Machine Learning Algorithms," in 2022 Second Int. Conf. Artif. Intell. Smart Energy (ICAIS), Feb. 2022, pp. 349-353.
38. [38] F. Y. Osisanwo, J. E. T. Akinsola, O. Awodele, J. O. Hinmikaiye, O. Olakanmi, and J. Akinjobi, "Supervised machine learning algorithms: classification and comparison," Int. J. Comput. Trends Technol. (IJCTT), vol. 48, no. 3, pp. 128-138, 2017.
39. [39] L. E. Peterson, "K-nearest neighbor," Scholarpedia, vol. 4, no. 2, p. 1883, 2009.
40. [40] M. N. Murty and R. Raghava, "Kernel-based SVM," in Support vector machines and perceptrons: Learning, optimization, classification, and application to social networks, 2016, pp. 57-67.
41. [41] B. Charbuty and A. Abdulazeez, "Classification based on decision tree algorithm for machine learning," J. Appl. Sci. Technol. Trends, vol. 2, no. 01, pp. 20-28, 2021.
42. [42] J. Ali, R. Khan, N. Ahmad, and I. Maqsood, "Random forests and decision trees," Int. J. Comput. Sci. Issues (IJCSI), vol. 9, no. 5, p. 272, 2012.
43. [43] Kaggle, "Loan Status Prediction," Available: https://www.kaggle.com/datasets/bhavikjikadara/loan-status-prediction/data.
44. [44] M. Cinelli et al., "Feature selection using a one dimensional naïve Bayes’ classifier increases the accuracy of support vector machine classification of CDR3 repertoires," Bioinformatics, vol. 33, no. 7, pp. 951-955, 2017.
45. [45] A. S. Paramita and S. V. Winata, "A comparative study of feature selection techniques in machine learning for predicting stock market trends," J. Appl. Data Sci., vol. 4, no. 3, pp. 147-162, 2023.
46. [46] D. M. Belete and M. D. Huchaiah, "Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results," Int. J. Computers and Applications, vol. 44, no. 9, pp. 875-886, 2022.
47. [47] A. T. Sarizeybek and O. Sevli, "A comparative analysis of bank customers' loan propensity using machine learning methods," J. Intell. Syst. Theory Appl., vol. 5, no. 2, pp. 137-144, 2022. [Online]. Available: https://doi.org/10.38016/jista.1036047
48. [48] D. Dansana, S. G. K. Patro, B. K. Mishra, V. Prasad, A. Razak, and A. W. Wodajo, "Analyzing the impact of loan features on bank loan prediction using Random Forest algorithm," Engineering Reports, vol. 6, no. 2, p. e12707, 2024.
49. [49] J. Stavins, "Credit card borrowing, delinquency, and personal bankruptcy," New Engl. Econ. Rev., pp. 15-30, 2000.
50. [50] C. L. Escalante, J. E. Epperson, and U. Raghunathan, "Gender bias claims in farm service agency's lending decisions," J. Agric. Resour. Econ., pp. 332-349, 2009.
51. [51] S. Kuznets, "Economic growth and income inequality," in The gap between rich and poor, Routledge, 2019, pp. 25-37.
52. [52] D. Oh, E. A. Buck, and A. Todorov, "Revealing hidden gender biases in competence impressions of faces," Psychol. Sci., vol. 30, no. 1, pp. 65-79, 2019.
53. [53] A. Bandyopadhyay, "Studying borrower level risk characteristics of education loan in India," IIMB Management Review, vol. 28, no. 3, pp. 126-135, 2016.
54. [54] C. Jamir and T. Z. Ezung, "Impact of education on employment, income, and poverty in Nagaland," Int. J. Res. Econ. Soc. Sci. (IJRESS), vol. 7, no. 9, pp. 50-56, 2017.
55. [55] A. Lusardi, "Financial literacy and the need for financial education: Evidence and implications," Swiss J. Econ. Stat., vol. 155, no. 1, pp. 1-8, 2019.
56. [56] E. Ravina, "Love & loans: The effect of beauty and personal characteristics in credit markets," SSRN Working Paper, 2019.
57. [57] O. Netzer, A. Lemaire, and M. Herzenstein, "When words sweat: Identifying signals for loan default in the text of loan applications," J. Marketing Res., vol. 56, no. 6, pp. 960-980, 2019.
58. [58] H. K. Mutegi, P. W. Njeru, and N. T. Ongesa, "Financial literacy and its impact on loan repayment by small and medium entrepreneurs," Int. J. Econ. Commerce Manag., vol. 3, no. 3, pp. 1-28, 2015.
59. [59] M. Li, A. Mickel, and S. Taylor, "‘Should this loan be approved or denied?’: A large dataset with class assignment guidelines," J. Stat. Educ., vol. 26, no. 1, pp. 55-66, 2018.
60. [60] R. Van Ooijen, and M. C. Van Rooij, "Mortgage risks, debt literacy and financial advice," Journal of Banking & Finance, vol. 72, pp. 201-217, 2016.
61. [61] B. Venkatesh, and J. Anuradha, "A review of feature selection and its methods," Cybernetics and Information Technologies, vol. 19, no. 1, pp. 3-26, 2019.
62. [62] Y. Xiao, C. Xing, T. Zhang, and Z. Zhao, "An intrusion detection model based on feature reduction and convolutional neural networks," IEEE Access, vol. 7, pp. 42210-42219, 2019.
63. [63] P. Dhal, and C. Azad, “A comprehensive survey on feature selection in the various fields of machine learning,” Applied Intelligence, vol. 52, no. 4, pp. 4543-4581, 2022.
64. [64] N. Pudjihartono, T. Fadason, A. W. Kempa-Liehr, and J. M. O'Sullivan, “A review of feature selection methods for machine learning-based disease risk prediction,” Frontiers in Bioinformatics, vol. 2, pp. 927312, 2022.
65. [65] R. C. Chen, C. Dewi, S. W. Huang, and R. E. Caraka, “Selecting critical features for data classification based on machine learning methods,” Journal of Big Data, vol. 7, no. 1, pp. 52, 2020.
66. [66] E. G. Adagbasa, S. A. Adelabu, and T. W. Okello, “Application of deep learning with stratified K-fold for vegetation species discrimation in a protected mountainous region using Sentinel-2 image,” Geocarto International, vol. 37, no. 1, pp. 142-162, 2022.
67. [67] R. Valavi, G. Guillera‐Arroita, J. J. Lahoz‐Monfort, and J. Elith, “Predictive performance of presence‐only species distribution models: a benchmark study with reproducible code,” Ecological Monographs, vol. 92, no. 1, pp. e01486, 2022.