RMT-Net: Reject-aware Multi-Task Network for Modeling Missing-not-at-random Data in Financial Credit Scoring

TL;DR

This paper introduces RMT-Net, a multi-task learning model that effectively addresses missing-not-at-random bias in financial credit scoring by leveraging the correlation between rejection and default classification tasks.

Contribution

The paper proposes the first multi-task learning approach, RMT-Net, to model biased credit scoring data by jointly learning rejection and default tasks with a gating mechanism.

Findings

RMT-Net outperforms baseline models on multiple datasets.

RMT-Net++ further enhances performance in complex rejection scenarios.

The approach effectively utilizes rejection information to improve default prediction accuracy.

Abstract

In financial credit scoring, loan applications may be approved or rejected. We can only observe default/non-default labels for approved samples but have no observations for rejected samples, which leads to missing-not-at-random selection bias. Machine learning models trained on such biased data are inevitably unreliable. In this work, we find that the default/non-default classification task and the rejection/approval classification task are highly correlated, according to both real-world data study and theoretical analysis. Consequently, the learning of default/non-default can benefit from rejection/approval. Accordingly, we for the first time propose to model the biased credit scoring data with Multi-Task Learning (MTL). Specifically, we propose a novel Reject-aware Multi-Task Network (RMT-Net), which learns the task weights that control the information sharing from the rejection/approval task to the default/non-default task by a gating network based on rejection probabilities. RMT-Net leverages the relation between the two tasks that the larger the rejection probability, the more the default/non-default task needs to learn from the rejection/approval task. Furthermore, we extend RMT-Net to RMT-Net++ for modeling scenarios with multiple rejection/approval strategies. Extensive experiments are conducted on several datasets, and strongly verifies the effectiveness of RMT-Net on both approved and rejected samples. In addition, RMT-Net++ further improves RMT-Net's performances.