Loan Default Prediction Using Artificial Intelligence for the Borrow – Lend Collaboration
Pages 256 - 270
Abstract
In the lending industry, such as banks or finance companies, investors provide loans to borrowers in exchange for the promise of repayment with interest. This two-way collaboration has many potential risks that need to be assessed. If the borrower repays the loan, then the lender would make a profit from the interest. However, if the borrower fails to repay the loan, then the lender loses money. Therefore, lenders face predicting the risk of a borrower being unable to repay a loan at any step of the credit process. Many financial institutes calculate FICO scores of a customer based on some factors such as the Payment History (35%), Amounts owed (30%), Length of credit history (15%), Credit mix (10%), and New credit (10% of the total point) of the customer, that score qualifies how risk customers are, how repayment ability of the customer. FICO score (Fair Isaac Corporation) is a traditional approach used broadly in finance fields to estimate risks and give a worthy credit amount to the customer. In this study, a new way is to use Artificial intelligence to predict the above problems. It bases on credit information and more personal information of the customers to predict its repayment ability. The data collected from VietCredit Finances used for training several Machine Learning models to determine if the borrower can repay its loan. Some linear, nonlinear models involved are Logistic Regression, Linear Discriminant Analysis, K Nearest Neighbors, Decision Tree, Naïve Bayes, Support Vector Machine. The algorithm turning and Boosting and Bagging ensemble methods were also used to determine the best model. As a result, the Gradient Boosting model was the outperform and optimal predictive model (PR-AUC metric = 0.957).
1. References
[1]
[2]
[3]
https://your.fitch.group/rs/732-CKH-767/images/Fitch_10079224.pdf. Accessed 4 Apr 2021
[4]
Aslam, U., Tariq, A., Hafiz, I., Sohail, A., Batcha, N.K.: An empirical study on loan default prediction models. J. Comput. Theoretical Nanosci. 16(8), 3483–3488 (2019). American Scientific Publishers
[5]
Turkson, R.E., Baagyere, E.Y., Wenya, G.E.: A machine learning approach for predicting bank creditworthiness. In: Proceedings of the third International Conference on Artificial Intelligence and Pattern Recognition (AIPR), Lodz, pp. 1–7 (2016).
[6]
Sheikh, M.A., Goel, A.K., Kumar, T.: An approach for prediction of loan approval using machine learning algorithm. In: Proceedings of the International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, pp. 490–494 (2020).
[7]
Pandey, T.N., Jagadev, A.K., Mohapatra, S.K., Dehuri, S.: Credit risk analysis using machine learning classifiers. In: Proceedings of the International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), Chennai, pp. 1850–1854 (2017).
[8]
Shiv, S.J., Murthy, S., Challuru, K.: Credit risk analysis using machine learning techniques. In: Proceedings of the 14th International Conference on Information Processing (CIPRO), Bangalore, India, pp. 1–5 (2018).
[9]
Qiu, W.: Credit risk prediction in an imbalanced social lending environment based on XGBoost. In: Proceedings of the 5th International Conference on Big Data and Information Analytics (BigDIA), Kunming, China, pp. 150–156 (2019).
[10]
Chen, S., Wang, Q., Liu, S.: Credit risk prediction in peer-to-peer lending with ensemble learning framework. In: Proceedings of the Chinese Control And Decision Conference (CCDC), Nanchang, China, pp. 4373–4377 (2019).
[11]
Alexandru, C., Maer-Matei, M.M., Albu, C.: Predictive models for loan default risk assessment. Econ. Comput. Econ. Cybern. Stud. Res. 53(2). Bucharest 149–165 (2019). University of Economic Studies
[12]
Zhu, L., Dafeng, Q., Daji, E., Cai, Y., Kuiyi, L.: A study on predicting loan default based on the random forest algorithm. Proc. Comput. Sci. 162, 503–513 (2019). Elsevier B.V.
[13]
Soares, L.M.J, Nardini, F.M., Renso, C., Fernandes, J.A.M.: An empirical comparison of classification algorithms for imbalanced credit scoring datasets. In: Proceedings of the 18th IEEE International Conference on Machine Learning And Applications (ICMLA), Boca Raton, FL, USA, pp. 747–754 (2019).
[14]
Shoumo, S.Z.H., Dhruba, M.I.M., Hossain, S., Ghani, N.H., Arif, H., Islam, S.: Application of machine learning in credit risk assessment: a prelude to smart banking. In: TENCON 2019 - IEEE Region 10 Conference (TENCON), Kochi, India, pp. 2023–2028 (2019).
[15]
Lawi, A., Aziz, F., Syarif, S.: Ensemble GradientBoost for increasing classification accuracy of credit scoring. In: Proceedings of the 4th International Conference on Computer Applications and Information Processing Technology (CAIPT), Kuta Bali, pp. 1–4 (2017).
[16]
Ferreira, L.E.B., Barddal, J.P., Gomes, H.M., Enembreck, F.: Improving credit risk prediction in online peer-to-peer (P2P) lending using imbalanced learning techniques. In: Proceedings of the IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), Boston, MA, pp. 175–181 (2017).
[17]
Chen, Y., Zhang, J., Ng, W.W.Y.: Loan default prediction using diversified sensitivity undersampling. In: Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC), Chengdu, pp. 240–245 (2018).
[18]
Barboza, F., Herbert, K., Edward, A.: Machine learning models and bankruptcy prediction. Expert Syst. Appl. 83, 405–417 (2017).
[19]
Namvar, A., Mohammad, S., Fethi, R., Mohsen, N.: Credit risk prediction in an imbalanced social lending environment. Int. J. Comput. Intell. Syst. 11(1), 925–935 (2019).
Recommendations
Informed Bond Trading, Corporate Yield Spreads, and Corporate Default Prediction
Taking advantage of recently augmented corporate bond transaction data, we examine the pricing implications of informed trading in corporate bonds and its ability to predict corporate defaults. We find that microstructure measures of information ...
Micro-lending Default Awareness Using Artificial Neural Network
ICMSSP 2017: Proceedings of the 2017 2nd International Conference on Multimedia Systems and Signal ProcessingLending ways plays as a key sector in banking business. In recent years, small amount lending, so-called micro-lending, has become the popular trend due to the prosperous development of internet financial service. The high profit has driven banks to ...
Credit Default Swaps and Debt Overhang
We analyze the impact of credit default swaps (CDSs) trading on firm investment, long-term debt financing, and valuation. In our model, the firm is endowed with a real option to initiate a project and enhance its future growth. Its creditors have access ...
Comments
Information & Contributors
Information
Published In
© Springer Nature Switzerland AG 2021.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 24 October 2021
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Jan 2025