Financial Inclusion and Alternate Credit Scoring: Role of Big Data and Machine Learning in Fintech

Abstract

We use unique and proprietary data from a large Fintech lender in India combined with machine learning models to document that alternative data captured from an individual’s mobile phone, such as the number and types of apps installed, measures of social connections, and borrowers’ “deep social footprints” based on call logs, can substitute for traditional credit bureau scores in credit risk evaluation and improve financial inclusion. Using machine learning-based prediction counterfactual analysis, we find that alternate credit scoring based on an individual's digital presence can expand credit access to financially excluded individuals who lack credit scores without adversely impacting default outcomes. Our findings imply that alternative digital data sources have the potential to significantly improve credit risk assessment and financial inclusion in developing countries.

Keywords: Fintech, Big data, Credit scores, Financial inclusion, Lending, Machine learning, Mobile footprint, Prediction Counterfactual, Social footprint, Social capital, Digital economy, Open banking, Data sharing

JEL Classification: G20, G21, G29