Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions

TL;DR

This paper systematically catalogs and clarifies the various assumptions, choices, and fairness definitions in the rapidly evolving field of prediction-based decision-making using machine learning, providing a valuable reference for researchers.

Contribution

It offers a comprehensive, notationally consistent catalogue of fairness definitions and clarifies the assumptions underlying prediction-based decisions in ML.

Findings

Identifies common assumptions in prediction-based decision systems

Provides a unified notation for fairness definitions

Highlights how assumptions impact fairness considerations

Abstract

A recent flurry of research activity has attempted to quantitatively define "fairness" for decisions based on statistical and machine learning (ML) predictions. The rapid growth of this new field has led to wildly inconsistent terminology and notation, presenting a serious challenge for cataloguing and comparing definitions. This paper attempts to bring much-needed order. First, we explicate the various choices and assumptions made---often implicitly---to justify the use of prediction-based decisions. Next, we show how such choices and assumptions can raise concerns about fairness and we present a notationally consistent catalogue of fairness definitions from the ML literature. In doing so, we offer a concise reference for thinking through the choices, assumptions, and fairness considerations of prediction-based decision systems.