Title: Loan delinquency analysis using predictive model

Authors: Riktesh Srivastava; Sachin Kumar Srivastava; Khushboo Agnihotri; Anviti Gupta

Addresses: City University, Ajman, P.O. Box 18484, Sheikh Ammar Road, Al Tallah 2 Ajman, UAE ' Sharda School of Business Studies, Sharda University, Agra, India ' Amity Business School, Amity University, Amity Rd., Sector 125, Noida, Uttar Pradesh 201301, India ' Sharda University, Plot No. 32-34, Knowledge Park III, Greater Noida, Uttar Pradesh 201310, India

Abstract: The research uses a machine learning approach to appraising the validity of customer aptness for a loan. Banks and non-banking financial companies (NBFC) face significant non-performing assets (NPAs) threats because of the non-payment of loans. In this study, the data is collected from Kaggle and tested using various machine learning models to determine if the borrower can repay its loan. In addition, we analysed the performance of the models [K-nearest neighbours (K-NN), logistic regression, support vector machines (SVM), decision tree, naive Bayes and neural networks]. The purpose is to support decisions that are based not on subjective aspects but objective data analysis. This work aims to analyse how objective factors influence borrowers to default loans, identify the leading causes contributing to a borrower's default loan. The results show that the decision tree classifier gives the best result, with a recall rate of 0.0885 and a false- negative rate of 5.4%.

Keywords: non-banking financial companies; NBFC; K-nearest neighbours; K-NN; decision tree; support vector machine; SVM; logistic regression; naïve Bayes; neural network.

DOI: 10.1504/IJKL.2024.141804

International Journal of Knowledge and Learning, 2024 Vol.17 No.6, pp.615 - 627

Received: 19 Oct 2021
Accepted: 05 Nov 2022
Published online: 02 Oct 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article