Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability

TL;DR

This paper demonstrates that simplicity in prediction models can lead to increased inequity and bias, highlighting a fundamental trade-off between interpretability and fairness in decision-making algorithms.

Contribution

The paper introduces a formal framework showing that simple prediction functions are inherently improvable and can induce biases against disadvantaged groups, revealing a fundamental conflict between simplicity and equity.

Findings

Simple prediction functions are strictly improvable for better efficiency and fairness.

Simplicity reduces overall welfare and harms disadvantaged groups.

Simplification creates incentives for biased use of group membership information.

Abstract

Algorithms are increasingly used to aid, or in some cases supplant, human decision-making, particularly for decisions that hinge on predictions. As a result, two additional features in addition to prediction quality have generated interest: (i) to facilitate human interaction and understanding with these algorithms, we desire prediction functions that are in some fashion simple or interpretable; and (ii) because they influence consequential decisions, we also want them to produce equitable allocations. We develop a formal model to explore the relationship between the demands of simplicity and equity. Although the two concepts appear to be motivated by qualitatively distinct goals, we show a fundamental inconsistency between them. Specifically, we formalize a general framework for producing simple prediction functions, and in this framework we establish two basic results. First, every simple prediction function is strictly improvable: there exists a more complex prediction function that is both strictly more efficient and also strictly more equitable. Put another way, using a simple prediction function both reduces utility for disadvantaged groups and reduces overall welfare relative to other options. Second, we show that simple prediction functions necessarily create incentives to use information about individuals' membership in a disadvantaged group --- incentives that weren't present before simplification, and that work against these individuals. Thus, simplicity transforms disadvantage into bias against the disadvantaged group. Our results are not only about algorithms but about any process that produces simple models, and as such they connect to the psychology of stereotypes and to an earlier economics literature on statistical discrimination.