Predicting Credit Risk : Using Machine Learning Algorithms to Predict the Creditworthiness of Borrowers and Determine their Likelihood of Defaulting on Loans in Nigeria
 |
International Journal of Recent Engineering Science (IJRES) |  |
| © 2023 by IJRES Journal | ||
| Volume-10 Issue-2 |
||
| Year of Publication : 2023 | ||
| Authors : Akinmoluwa Oluseye Ayobami, Odeajo Israel, Jimoh Yusuf, Afolabi Moses Eniola |
||
| DOI : 10.14445/23497157/IJRES-V10I2P107 |
How to Cite?
Akinmoluwa Oluseye Ayobami, Odeajo Israel, Jimoh Yusuf, Afolabi Moses Eniola, "Predicting Credit Risk : Using Machine Learning Algorithms to Predict the Creditworthiness of Borrowers and Determine their Likelihood of Defaulting on Loans in Nigeria," International Journal of Recent Engineering Science, vol. 10, no. 2, pp. 46-53, 2023. Crossref, https://doi.org/10.14445/23497157/IJRES-V10I2P107
Abstract
Due to recent advancements in the financial sector and the increasing need for obtaining loans, a significant number of people have begun to apply for bank loans. The rising rate of loan defaults is one of the most significant challenges the banking industry faces in the current economy. It is becoming increasingly challenging for banking authorities to precisely evaluate loan applications and creditworthiness, thereby mitigating the risk of individuals defaulting on loans. The present study proposed four different machine learning models that seek to predict an individual's eligibility for loan approval based on the evaluation of certain attributes, thereby aiding the banking authorities by facilitating the selection of suitable candidates from a given list of loan applicants. This paper provides a thorough comparison and analysis of four algorithms: Decision Trees, Gradient Boosting Classifiers, Random Forest, and Gaussian NB. The prediction is based on zindi Africa data. Important evaluation metrics, including Confusion Matrix, Accuracy, Recall, Precision, and F1-Score, have been calculated and presented in our result. In terms of accuracy, the Gaussian NB Algorithm outperformed the other three algorithms by a margin of 77%.
Keywords
Credit Risk, Credit Score, Decision Trees, Gaussian NB, Gradient Boosting, Loan Prediction, Machine Learning, Random Forest.
Reference
[1] Maisa Cardoso Aniceto, Flavio Barboza, and Herbert Kimura, “Machine Learning Predictivity Applied to Consumer Creditworthiness,” Future Business Journal, vol. 6, no. 1, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] [Online]. Available: https://www.statista.com/outlook/dmo/fintech/digital-capital-raising/marketplace-lending-consumer/nigeria
[3] Isa Fatima, and Isa Rehanet, “Treatment of Toxic Asset by Deposit Money Banks in Nigeria: A Review of Literature,” TSU-International Journal of Accounting and Finance, vol. 1, no. 1, pp. 42-50, 2021.
[Google Scholar] [Publisher Link]
[4] [Online]. Available: https://www.cbn.gov.ng/out/2013/ofisd/revised%20guidelines%20for%20primary%20mortgage%20banks%20in%20nigeria.pdf
[5] Fernanda Assef et al., “Classification Algorithms in Financial Application: Credit Risk Analysis on Legal Entities,” IEEE Latin America Transactions, vol. 17, no. 10, pp. 1733-1740, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Saba Moradi, and Farimah Mokhatab Rafiei, “A Dynamic Credit Risk Assessment Model with Data Mining Techniques: Evidence from Iranian Banks,” Financial Innovation, vol. 5, no. 1, pp. 1-27, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] G. S. Samanvitha et al., “Machine Learning Based Consumer Credit Risk Prediction,” Sustainable Advanced Computing, pp. 113-123, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Seyyide Doğan, Yasin Büyükkör, and Murat Atan, “A Comparative Study of Corporate Credit Ratings Prediction with Machine Learning,” Operations Research and Decisions, vol. 32, no. 1, pp. 25-47, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Swati Tyagi, “Analyzing Machine Learning Models for Credit Scoring with Explainable AI and Optimizing Investment Decisions,” American International Journal of Business Management, vol. 5, no. 1, pp. 5-19, 2022.
[Google Scholar] [Publisher Link]
[10] Ekaterina V. Orlova, “Methodology and Models for Individuals’ Creditworthiness Management Using Digital Footprint Data and Machine Learning Methods,” Mathematics, vol. 9, no. 15, p. 1820, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Alaba, O.B., Taiwo, E.O., and Abass, O.A., “Data Mining Algorithm for Development of a Predictive Model for Mitigating Loan Risk in Nigerian Banks,” Journal of Applied Sciences and Environmental Management, vol. 25, no. 9, pp.1613-1616, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Akinwunmi Adeboye A, and Dare Festus Oluwafemi, “Machine Learning Approach to Credit Scoring for Fintech Start-Ups Using Micro Finance Banks in Nigeria,” International Journal of Innovative Research and Development, vol. 11, no. 8, pp. 97-109, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mehul Madaan, “Loan Default Prediction Using Decision Trees and Random Forest: A Comparative Study,” IOP Conference Series: Materials Science and Engineering, vol. 1022, no. 1, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Pagadala Suganda Devi, "Credit Risk Management Practices of Micro Finance Institutions in Ethiopia– A Brief Literature Review," SSRG International Journal of Economics and Management Studies, vol. 4, no. 1, pp. 10-16, 2017.
[CrossRef] [Publisher Link]
[15] Kush R. Varshney, “Trustworthy Machine Learning and Artificial Intelligence,” XRDS: Crossroads, the ACM Magazine for Students, vol. 25, no. 3, pp. 26-29, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Liaqat Ali et al., “A Feature-Driven Decision Support System for Heart Failure Prediction Based on Statistical Model and Gaussian Naive Bayes,” Computational and Mathematical Methods in Medicine, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Breiman, L., Random Forests, Machine Learning, pp. 5-32, 2001.
[18] Iqbal H. Sarker, “Machine Learning: Algorithms, Real-World Applications and Research Directions,” SN Computer Science, vol. 2, no. 3, p.160, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Larysa Zomchak, and Viktoria Melnychuk, “Creditworthiness of Individual Borrowers Forecasting with Machine Learning Methods,” Advances in Artificial Systems for Medicine and Education VI, vol. 159, pp. 553-561, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Alexandru Coser, “Predictive Models for Loan Default Risk Assessment,” Economic Computation & Economic Cybernetics Studies & Research, vol. 53, no. 2, pp. 149-165, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Lin Zhu, “A Study on Predicting Loan Default Based on the Random Forest Algorithm,” Procedia Computer Science, vol. 162, pp. 503- 513, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Lee Victor, and Mafas Raheem, “Loan Default Prediction Using Genetic Algorithm: A Study Within Peer-to-Peer Lending Communities,” International Journal of Innovative Science and Research Technology, vol. 6, no. 3, pp. 2456-2165, 2021.
[Google Scholar] [Publisher Link]
[23] Pradeep Sudhakaran, and Sujoy Baitalik, “Xgboost Optimized by Adaptive Tree Parzen Estimators for Credit Risk Analysis,” 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Vinay Padimi et al., “Applying Machine Learning Techniques to Maximize the Performance of Loan Default Prediction,” Journal of Neutrosophic and Fuzzy System, vol. 2, no. 2, pp. 44-56, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Shrikant Kokate, and Manna Sheela Rani Chetty, “Credit Risk Assessment of Loan Defaulters in Commercial Banks Using Voting Classifier Ensemble Learner Machine Learning Model,” International Journal of Safety and Security Engineering, vol. 11, no. 5, pp. 565- 572, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[26] [Online]. Available: https://zindi.africa/competitions/data-science-nigeria-challenge-1-loan-default-prediction/data
[27] Kotsiantis, S.B., Zaharakis, I.D., and Pintelas, P.E., “Machine Learning: A Review of Classification and Combining Techniques,” Artificial Intelligence Review, vol. 26, no. 3, pp. 159-190, 2006.
[CrossRef] [Google Scholar] [Publisher Link]