Predicting Educational Loan Defaults: Application of Machine Learning and Deep Learning Models

46 Pages Posted: 27 Dec 2019 Last revised: 4 Dec 2021

See all articles by M Jayadev

M Jayadev

Indian Institute of Management (IIMB), Bangalore

Neel Shah

Columbia Business School

Ravi Vadlamani

Institute for Development and Research in Banking Technologies

Date Written: December 4, 2021

Abstract

Student (educational) loans are highly vulnerable to default risk and thus guaranteed by governments. We show that collateral-free educational loans are a case for the application of Machine Learning models to predict default factors with greater accuracy, helping banks in risk management and the government in designing economic policies of interest suspension and credit guarantees. We argue that heterogeneous ensembles constructed using stacking or a Hill Climb Ensemble approach are most suited for imbalanced data set since the interaction between diverse features would create non-linearities that are impossible to model using a single algorithm. Borrower/student social background emerges as an important feature explaining the loan defaults, warranting a correction in the public policy in designing the educational loan schemes for under privileged borrowers. Our paper also shows that Machine learning models are not systematically biased against underprivileged borrowers and do not lead banks to refuse credit. Ours is the first study to apply Statistical, Machine learning and Deep learning Models on a data set of student loans.

Keywords: Credit Risk, Educational Loans, Statistical Techniques, Artificial Intelligence Techniques

Suggested Citation

Jayadev, M and Shah, Neel and Vadlamani, Ravi, Predicting Educational Loan Defaults: Application of Machine Learning and Deep Learning Models (December 4, 2021). IIM Bangalore Research Paper No. 601 (2019), Available at SSRN: https://ssrn.com/abstract=3510012 or http://dx.doi.org/10.2139/ssrn.3510012

M Jayadev (Contact Author)

Indian Institute of Management (IIMB), Bangalore

Bannerghatta Road
Bangalore, Karnataka 560076
India

Neel Shah

Columbia Business School ( email )

India

Ravi Vadlamani

Institute for Development and Research in Banking Technologies ( email )

Castle Hills, Road No.1
Masab Tank, Hyderabad 500 057
India

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
168
Abstract Views
720
rank
229,179
PlumX Metrics