Enhancing User' s Income Estimation with Super-App Alternative Data

TL;DR

This paper demonstrates that alternative data from Super-Apps significantly improves user income estimation models over traditional bureau methods by capturing behavioral patterns with interpretability tools.

Contribution

It introduces the use of Super-App data for income estimation and applies TreeSHAP for interpretability, showing the added predictive value of behavioral data.

Findings

Super-App data outperforms traditional bureau income estimators.

Behavioral and transactional patterns have strong predictive power.

Incentivizes financial institutions to incorporate alternative data.

Abstract

This paper presents the advantages of alternative data from Super-Apps to enhance user' s income estimation models. It compares the performance of these alternative data sources with the performance of industry-accepted bureau income estimators that takes into account only financial system information; successfully showing that the alternative data manage to capture information that bureau income estimators do not. By implementing the TreeSHAP method for Stochastic Gradient Boosting Interpretation, this paper highlights which of the customer' s behavioral and transactional patterns within a Super-App have a stronger predictive power when estimating user' s income. Ultimately, this paper shows the incentive for financial institutions to seek to incorporate alternative data into constructing their risk profiles.