Feature-Level Fusion of Super-App and Telecommunication Alternative Data Sources for Credit Card Fraud Detection

TL;DR

This paper explores a feature-level data fusion approach combining super-app, telecommunication, and traditional credit data to improve early detection of credit card fraud, achieving a ROC AUC of 0.81.

Contribution

It introduces a novel framework for integrating diverse data sources at the feature level for fraud detection, demonstrating improved performance over traditional methods.

Findings

Fusion of alternative and traditional data improves detection accuracy.

Achieved ROC AUC of 0.81 with the proposed model.

Evaluation includes financial cost metrics.

Abstract

Identity theft is a major problem for credit lenders when there's not enough data to corroborate a customer's identity. Among super-apps large digital platforms that encompass many different services this problem is even more relevant; losing a client in one branch can often mean losing them in other services. In this paper, we review the effectiveness of a feature-level fusion of super-app customer information, mobile phone line data, and traditional credit risk variables for the early detection of identity theft credit card fraud. Through the proposed framework, we achieved better performance when using a model whose input is a fusion of alternative data and traditional credit bureau data, achieving a ROC AUC score of 0.81. We evaluate our approach over approximately 90,000 users from a credit lender's digital platform database. The evaluation was performed using not only traditional ML metrics but the financial costs as well.