Working Paper: NBER ID: w25854
Authors: Jon Kleinberg; Sendhil Mullainathan
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.
Keywords: algorithms; decision-making; fairness; equity; interpretability
JEL Codes: C54; C55; D8; I30; J7; K00
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| simple prediction functions (C29) | bias against disadvantaged groups (J15) |
| simple prediction functions (C29) | reduced utility for disadvantaged groups (R28) |
| simple prediction functions (C29) | diminished overall welfare compared to complex alternatives (D69) |
| complex prediction functions (C39) | higher efficiency and greater equity (D61) |
| simplification in decision-making processes (D91) | biases against disadvantaged groups (J15) |
| simple prediction functions (C29) | incentives to use information about group membership (C92) |
| incentives to use information about group membership (C92) | discriminatory outcomes against disadvantaged individuals (J70) |