Enhancing Data Quality through Self-learning on Imbalanced Financial Risk Data

TL;DR

This paper introduces TriEnhance, a novel data pre-processing method that improves financial risk prediction models by generating synthetic minority class samples, filtering, and self-learning, leading to better minority class calibration.

Contribution

The paper presents TriEnhance, a simple yet effective technique for augmenting imbalanced financial risk datasets through synthetic sample generation, filtering, and pseudo-labeling.

Findings

TriEnhance improves minority class calibration across six benchmark datasets.

The method enhances the detection of high-risk instances in financial datasets.

Results show significant performance gains over baseline models.

Abstract

In the financial risk domain, particularly in credit default prediction and fraud detection, accurate identification of high-risk class instances is paramount, as their occurrence can have significant economic implications. Although machine learning models have gained widespread adoption for risk prediction, their performance is often hindered by the scarcity and diversity of high-quality data. This limitation stems from factors in datasets such as small risk sample sizes, high labeling costs, and severe class imbalance, which impede the models' ability to learn effectively and accurately forecast critical events. This study investigates data pre-processing techniques to enhance existing financial risk datasets by introducing TriEnhance, a straightforward technique that entails: (1) generating synthetic samples specifically tailored to the minority class, (2) filtering using binary feedback to refine samples, and (3) self-learning with pseudo-labels. Our experiments across six benchmark datasets reveal the efficacy of TriEnhance, with a notable focus on improving minority class calibration, a key factor for developing more robust financial risk prediction systems.