Fintech in Financial Inclusion: Machine Learning Applications in Assessing Credit Risk

35 Pages Posted: 6 Nov 2019

Date Written: May 2019


Recent advances in digital technology and big data have allowed FinTech (financial technology)lending to emerge as a potentially promising solution to reduce the cost of credit and increasefinancial inclusion. However, machine learning (ML) methods that lie at the heart of FinTech credithave remained largely a black box for the nontechnical audience. This paper contributes to theliterature by discussing potential strengths and weaknesses of ML-based credit assessment through(1) presenting core ideas and the most common techniques in ML for the nontechnical audience; and(2) discussing the fundamental challenges in credit risk analysis. FinTech credit has the potential toenhance financial inclusion and outperform traditional credit scoring by (1) leveraging nontraditionaldata sources to improve the assessment of the borrower's track record; (2) appraising collateral value;(3) forecasting income prospects; and (4) predicting changes in general conditions. However, becauseof the central role of data in ML-based analysis, data relevance should be ensured, especially insituations when a deep structural change occurs, when borrowers could counterfeit certain indicators,and when agency problems arising from information asymmetry could not be resolved. To avoiddigital financial exclusion and redlining, variables that trigger discrimination should not be used toassess credit rating.

Keywords: Credit risk, Credit ratings, Risk management, Credit, Interest rates, FinTech Credit, Financial Inclusion, Machine Learning, Credit Risk Assessment, outcome variable, borrower, LGD, decision tree, cross-validation

JEL Classification: C52, C54, C55, G21, G23, C53, E01, E52, G32, K2

Suggested Citation

Bazarbash, Majid, Fintech in Financial Inclusion: Machine Learning Applications in Assessing Credit Risk (May 2019). IMF Working Paper No. 19/109, Available at SSRN:

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

Paper statistics

Abstract Views
PlumX Metrics