Home / Current Issue / Paper 1720272
A Study On Loan Default Prediction at Bajaj Finance Limited
Subject area: Management and Commerce · Area of research: Loan Default Prediction
DOI: https://doi.org/10.64388/IREV10I2-1720272
Abstract
Loan default remains one of the more persistent challenges facing non-banking financial companies, and Bajaj Finance Limited, as one of India's largest NBFCs, is no exception. This article examines the factors that shape borrowers' likelihood of default and the analytical approach through which such risk can be anticipated. Drawing on a structured survey of 101 respondents together with an underlying logistic regression framework, the study looks at how income level, EMI burden, existing liabilities, credit score, repayment history and exposure to unexpected expenses relate to repayment outcomes. It also outlines a probability-based classification scheme that sorts borrowers into low-, medium- and high-risk categories, a tool intended to support faster and more consistent credit decisions. The survey results show that respondents are drawn predominantly from younger, lower- and middle-income segments, that a substantial share have experienced delayed EMI payments at some point, and that poor financial planning, existing debt obligations and unexpected expenses are widely seen as significant contributors to repayment difficulty. Credit score and repayment history, meanwhile, are broadly recognised as central to loan approval and to predicting future behaviour. The article concludes that combining sound credit assessment with continuous account monitoring and predictive analytics allows lenders such as Bajaj Finance to identify risk earlier and manage it more effectively, supporting growth without compromising portfolio quality.
Keywords
Loan Default, Credit Risk, Bajaj Finance, NBFC, Logistic Regression, Risk Classification, Repayment Behaviour
How to cite this paper
@article{1720272,
author = {Dr. Chaitra K S, Kiran G N},
title = {A Study On Loan Default Prediction at Bajaj Finance Limited},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {76-85},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1720272.pdf},
abstract = {Loan default remains one of the more persistent challenges facing non-banking financial companies, and Bajaj Finance Limited, as one of India's largest NBFCs, is no exception. This article examines the factors that shape borrowers' likelihood of default and the analytical approach through which such risk can be anticipated. Drawing on a structured survey of 101 respondents together with an underlying logistic regression framework, the study looks at how income level, EMI burden, existing liabilities, credit score, repayment history and exposure to unexpected expenses relate to repayment outcomes. It also outlines a probability-based classification scheme that sorts borrowers into low-, medium- and high-risk categories, a tool intended to support faster and more consistent credit decisions. The survey results show that respondents are drawn predominantly from younger, lower- and middle-income segments, that a substantial share have experienced delayed EMI payments at some point, and that poor financial planning, existing debt obligations and unexpected expenses are widely seen as significant contributors to repayment difficulty. Credit score and repayment history, meanwhile, are broadly recognised as central to loan approval and to predicting future behaviour. The article concludes that combining sound credit assessment with continuous account monitoring and predictive analytics allows lenders such as Bajaj Finance to identify risk earlier and manage it more effectively, supporting growth without compromising portfolio quality.},
keywords = {Loan Default, Credit Risk, Bajaj Finance, NBFC, Logistic Regression, Risk Classification, Repayment Behaviour},
month = {August},
doi = {https://doi.org/10.64388/IREV10I2-1720272}
}