How Data Quality Affects Machine Learning Models for Credit Risk Assessment

TL;DR

This study examines how various data quality issues such as missing values, noise, outliers, and label errors impact the accuracy of machine learning models in credit risk assessment, highlighting the importance of data integrity.

Contribution

It introduces a systematic methodology and tools to evaluate the robustness of ML models against data corruption in credit risk prediction.

Findings

Model robustness varies significantly with data degradation type and severity.

The methodology enables practical assessment of data pipeline resilience.

Framework supports further research in data-centric AI robustness.

Abstract

Machine Learning (ML) models are being increasingly employed for credit risk evaluation, with their effectiveness largely hinging on the quality of the input data. In this paper we investigate the impact of several data quality issues, including missing values, noisy attributes, outliers, and label errors, on the predictive accuracy of the machine learning model used in credit risk assessment. Utilizing an open-source dataset, we introduce controlled data corruption using the Pucktrick library to assess the robustness of 10 frequently used models like Random Forest, SVM, and Logistic Regression and so on. Our experiments show significant differences in model robustness based on the nature and severity of the data degradation. Moreover, the proposed methodology and accompanying tools offer practical support for practitioners seeking to enhance data pipeline robustness, and provide researchers with a flexible framework for further experimentation in data-centric AI contexts.