Supporting Financial Inclusion with Graph Machine Learning and Super-App Alternative Data

TL;DR

This paper explores how Super-Apps' user interactions and graph-based machine learning methods can improve credit risk prediction, fostering more inclusive financial services.

Contribution

It introduces two graph-based methodologies for predicting borrower behavior within Super-Apps, highlighting new features that enhance credit risk models.

Findings

Graph centrality and neighbor behavior improve model accuracy.

Graph neural networks outperform traditional feature-based models.

Super-Apps can redefine credit risk assessment for financial inclusion.

Abstract

The presence of Super-Apps have changed the way we think about the interactions between users and commerce. It then comes as no surprise that it is also redefining the way banking is done. The paper investigates how different interactions between users within a Super-App provide a new source of information to predict borrower behavior. To this end, two experiments with different graph-based methodologies are proposed, the first uses graph based features as input in a classification model and the second uses graph neural networks. Our results show that variables of centrality, behavior of neighboring users and transactionality of a user constituted new forms of knowledge that enhance statistical and financial performance of credit risk models. Furthermore, opportunities are identified for Super-Apps to redefine the definition of credit risk by contemplating all the environment that their platforms entail, leading to a more inclusive financial system.