This tutorial identifies limitations in association-based approaches, introduces a causal-modeling framework for anti-discrimination learning, and suggests directions for future research.

Anti-discrimination learning addresses discrimination in data mining and machine learning. Discrimination discovery analyzes historical decision records to identify discriminatory practices, while discrimination prevention modifies biased data or predictive algorithms. Because discrimination is causal, demonstrating it requires evidence of a causal relationship rather than an association. Although association does not imply causation, this distinction has received limited attention in the literature.

Outline

The tutorial is organized into six parts: an introduction, a literature review, three technical sections, and a conclusion.