Measuring Fairness in Financial Transaction Machine Learning Models

2025-01-18

AI Summary

Assessing fairness of machine learning models in financial transactions remains challenging due to complex regulatory requirements, domain-specific operational constraints, and the need for actionable insights. Method: This paper proposes an interpretable, operationally grounded fairness evaluation framework tailored to credit usage prediction. It integrates causal inference, group fairness metrics (e.g., statistical parity, equal opportunity), counterfactual perturbation testing, and eXplainable AI (XAI) techniques to construct a multidimensional fairness metric system aligned with financial business logic and regulatory standards—specifically addressing cross-regional and cross-sectoral deployment scenarios. Contribution/Results: Evaluated via a closed-loop validation pipeline on real-world Mastercard transaction data, the framework identified significant geographic and industry-sensitive biases in production models, generated auditable diagnostic reports, and guided three iterative model refinements—increasing service coverage for high-risk groups by 12%. The work bridges the gap among theoretical fairness research, industrial ML practice, and AI governance.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Mastercard, a global leader in financial services, develops and deploys machine learning models aimed at optimizing card usage and preventing attrition through advanced predictive models. These models use aggregated and anonymized card usage patterns, including cross-border transactions and industry-specific spending, to tailor bank offerings and maximize revenue opportunities. Mastercard has established an AI Governance program, based on its Data and Tech Responsibility Principles, to evaluate any built and bought AI for efficacy, fairness, and transparency. As part of this effort, Mastercard has sought expertise from the Turing Institute through a Data Study Group to better assess fairness in more complex AI/ML models. The Data Study Group challenge lies in defining, measuring, and mitigating fairness in these predictions, which can be complex due to the various interpretations of fairness, gaps in the research literature, and ML-operations challenges.

Problem

• Machine Learning Fairness
• Monetary Transactions
• Ethical AI

Innovation

• AI governance
• machine learning fairness
• systematic approach