An implementation of machine learning on loan default prediction based on customer behavior

Robi Aziz Zuama; Nurul Ichsan; Achmad Baroqah Pohan; Mohammad Syamsul Azis; Mareanus Lase

Authors

Robi Aziz Zuama Fakultas Teknik & Informatika, Universitas Bina Sarana Informatika https://orcid.org/0000-0001-7955-9306
Nurul Ichsan Fakultas Teknik & Informatika, Universitas Bina Sarana Informatika
Achmad Baroqah Pohan Fakultas Teknik & Informatika, Universitas Bina Sarana Informatika
Mohammad Syamsul Azis Fakultas Teknologi Informasi, Universitas Nusa Mandiri
Mareanus Lase Fakultas Teknologi Informasi, Universitas Nusa Mandiri

Keywords:

Loan Default Prediction, Machine Learning, Customer Behavior Analysis, Financial Institution Challenges, Matrix Evaluation

Abstract

In the banking sector, loans have become a key component that steers the economy, encourages company expansion, and directly impacts the growth of a nation's economy. Banks must evaluate borrowers' ability to repay loans given the inherent risks involved in order to reduce the likelihood of default. In particular, machine learning (ML) has shown promise as a revolutionary tool for loan default prediction using advanced methodologies to examine historical data relating to customer behavior, this study investigates the application of machine learning (ML) in forecasting loan outcomes. The results show that XGBoost performs better than other machine learning algorithms, with an accuracy rate of 89%. Random forest and logistic regression come in second and third, respectively, with 88% accuracy. KNN and decision trees come next, both with somewhat lower accuracy rates (87%). By incorporating consumer behavior domain variables, this study fills in the gaps in the literature and offers a more thorough understanding of loan projections. In order to improve model performance and strengthen the predictive power of machine learning algorithms in loan scenarios, further research incorporating trials to optimize algorithm parameters is necessary as financial institutions continue to experience difficulties.

Downloads

Download data is not yet available.

References

U. Aslam, H. I. Tariq Aziz, A. Sohail, and N. K. Batcha, “An empirical study on loan default prediction models,” J. Comput. Theor. Nanosci., vol. 16, no. 8, pp. 3483–3488, 2019.

C. W. Su, F. Liu, M. Qin, and T. Chnag, “Is a consumer loan a catalyst for confidence?,” Econ. Res. Istraživanja, vol. 36, no. 2, p. 2142260, 2023.

K. Fatmawati, “GROSS DOMESTIC PRODUCT: Financing & Investment Activities and State Expenditures,” KINERJA J. Manaj. Organ. dan Ind., vol. 1, no. 1, pp. 11–18, 2022.

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), 2020, pp. 423–426. doi: 10.1109/SMART50582.2020.9336801.

G. T. H. Vuong, P. T. T. Phan, C. X. Nguyen, D. M. Nguyen, and K. D. Duong, “Liquidity creation and bank risk-taking: Evidence from a transition market,” Heliyon, vol. 9, no. 9, 2023.

N. Muhamad, “Gen Z dan Milenial Jadi Penyumbang Kredit Macet Pinjol Terbesar pada Juni 2023,” Databoks, p. 2023, 2023. [Online]. Available: https://databoks.katadata.co.id/datapublish/2023/08/23/gen-z-dan-milenial-jadi-penyumbang-kredit-macet-pinjol-terbesar-pada-juni-2023

S. I. Serengil, S. Imece, U. G. Tosun, E. B. Buyukbas, and B. Koroglu, “A Comparative Study of Machine Learning Approaches for Non Performing Loan Prediction,” in 2021 6th International Conference on Computer Science and Engineering (UBMK), 2021, pp. 326–331. doi: 10.1109/UBMK52708.2021.9558894.

J. W. Goodell, S. Kumar, W. M. Lim, and D. Pattnaik, “Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis,” J. Behav. Exp. Financ., vol. 32, p. 100577, 2021.

D. Mhlanga, “Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment,” Int. J. Financ. Stud., vol. 9, no. 3, p. 39, 2021.

I. Lee and Y. J. Shin, “Machine learning for enterprises: Applications, algorithm selection, and challenges,” Bus. Horiz., vol. 63, no. 2, pp. 157–170, 2020.

A. R. Provenzano et al., “Machine learning approach for credit scoring,” arXiv Prepr. arXiv2008.01687, 2020.

S. Sobana and P. J. L. Ebenezer, “A Comparative Study of Machine Learning Algorithms for Loan Approval Prediction,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 04, no. 12, p. 565, 2022.

T. Aditya Sai Srinivas, S. Ramasubbareddy, and K. Govinda, “Loan Default Prediction Using Machine Learning Techniques,” in Innovations in Computer Science and Engineering: Proceedings of the Ninth ICICSE, 2021, Springer, 2022, pp. 529–535.

S. Surana, “Loan Prediction Based on Customer Behavior,” kaggle.com, 2021. https://www.kaggle.com/datasets/subhamjain/loan-prediction-based-on-customer-behavior/data (accessed Dec. 18, 2023).

S. Maldonado, J. López, and C. Vairetti, “An alternative SMOTE oversampling strategy for high-dimensional datasets,” Appl. Soft Comput., vol. 76, pp. 380–389, 2019.

A. Das, “Logistic regression,” in Encyclopedia of Quality of Life and Well-Being Research, Springer, 2021, pp. 1–2.

J. C. Stoltzfus, “Logistic regression: a brief primer,” Acad. Emerg. Med., vol. 18, no. 10, pp. 1099–1104, 2011.

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.

I. S. Damanik, A. P. Windarto, A. Wanto, Poningsih, S. R. Andani, and W. Saputra, “Decision tree optimization in C4. 5 algorithm using genetic algorithm,” in Journal of Physics: Conference Series, IOP Publishing, 2019, p. 12012.

L. Breiman, “Random forests,” Mach. Learn., vol. 45, pp. 5–32, 2001.

T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794.

J. D. Novaković, A. Veljović, S. S. Ilić, Ž. Papić, and M. Tomović, “Evaluation of classification models in machine learning,” Theory Appl. Math. Comput. Sci., vol. 7, no. 1, p. 39, 2017.