Causal Inference for Social Discrimination Reasoning

TL;DR

This paper introduces a causal inference method using propensity scores to detect discriminatory bias in decision-making, addressing confounding factors often overlooked by correlation-based approaches.

Contribution

It presents a novel causal discrimination discovery framework that quantifies bias effects and visualizes discrimination patterns with regression trees, improving transparency.

Findings

Validated on two real-world datasets

Effective in identifying causal discrimination patterns

Enhances transparency in machine learning models

Abstract

The discovery of discriminatory bias in human or automated decision making is a task of increasing importance and difficulty, exacerbated by the pervasive use of machine learning and data mining. Currently, discrimination discovery largely relies upon correlation analysis of decisions records, disregarding the impact of confounding biases. We present a method for causal discrimination discovery based on propensity score analysis, a statistical tool for filtering out the effect of confounding variables. We introduce causal measures of discrimination which quantify the effect of group membership on the decisions, and highlight causal discrimination/favoritism patterns by learning regression trees over the novel measures. We validate our approach on two real world datasets. Our proposed framework for causal discrimination has the potential to enhance the transparency of machine learning with tools for detecting discriminatory bias both in the training data and in the learning algorithms.