Explainable AI Based Credit Risk Prediction for Loan Approval using CIBIL Score

DOI

10.2991/978-94-6239-799-6_12How to use a DOI?

Keywords

Credit Risk Assessment; Loan Approval Prediction; Machine Learning; Explainable AI (XAI); SHAP; CIBIL Score; Financial Risk Prediction; Loan Default Prediction

Abstract

Everyday bank gives loan to many people. Many people pay the loan whereas there are many people who don’t pay the loan. So, it is very difficult for bank to understand whom to give the loan. Because they don’t know the borrower. They don’t know which borrower will be able to pay the loan and which will not. Machine learning can be an alternative for this process but the main problem is that machine learning uses the advanced algorithm which is ‘black box’. The main problem is that black box only answers the “yes” or “no”. Black box does not give the explanation of why it has rejected or approved the loan.

In this project, we tried to solve this problem. We made a credit risk predictor which uses cibil score (we used the loan grade as a cibil score) and also used many financial features. We tested four different types of models in our dataset Logistic Regression, Decision Tree, Random Forest, and XGBoost. In our testing process XGBoost gave the best results.

After that we used a tool called SHAP (SHapley Additive Explanations) to understand why this model was giving the best result. SHAP showed us that there are three most reasons that decide whether to give the person the loan or not, Person Income, Loan Grade and Loan Percent Income are the three most important reasons. This system helps the bank to trust why this model is helpful for the banks and it also helps the customers because it tells them why their loan was approved or rejected.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ravi Sharma
AU  - Devesh Kumar Upadhyay
PY  - 2026
DA  - 2026/09/30
TI  - Explainable AI Based Credit Risk Prediction for Loan Approval using CIBIL Score
BT  - Proceedings of the International Conference on Emerging Trends and Technologies in Applications of Computer Science (ICETTACS 2026)
PB  - Atlantis Press
SP  - 157
EP  - 173
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-799-6_12
DO  - 10.2991/978-94-6239-799-6_12
ID  - Sharma2026
ER  -