FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring

2025-08-27

AI Summary

In predictive business process monitoring, sensitive attributes (e.g., gender, age) can induce unfair predictions—especially when used naively, without contextual grounding. To address this, we propose a human-in-the-loop fairness enhancement framework: (1) knowledge distillation from neural networks to decision trees enables interpretable modeling and precise identification of bias-inducing paths driven by sensitive attributes; (2) expert feedback guides model fine-tuning, supporting context-aware masking and reweighting of sensitive features. Crucially, our approach preserves the original process log structure and jointly optimizes fairness and predictive accuracy. Experiments on multiple real-world process datasets demonstrate substantial reductions in group fairness disparities—e.g., ΔDP and ΔEO—while maintaining high predictive performance (AUC degradation <1.2%). The method thus establishes an interpretable, intervention-enabled fairness assurance framework for trustworthy process intelligence.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Humans and AI: Human-in-the-loop Machine Learning
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Sensitive attributes like gender or age can lead to unfair predictions in machine learning tasks such as predictive business process monitoring, particularly when used without considering context. We present FairLoop1, a tool for human-guided bias mitigation in neural network-based prediction models. FairLoop distills decision trees from neural networks, allowing users to inspect and modify unfair decision logic, which is then used to fine-tune the original model towards fairer predictions. Compared to other approaches to fairness, FairLoop enables context-aware bias removal through human involvement, addressing the influence of sensitive attributes selectively rather than excluding them uniformly.

Problem

• Mitigating unfair predictions from sensitive attributes
• Enabling human-guided bias removal in neural networks
• Addressing context-aware fairness without uniform attribute exclusion

Innovation

• Human-guided bias mitigation tool
• Distills decision trees from neural networks
• Enables context-aware fairness through human involvement