Algorithmic Feature Highlighting for Human-AI Decision-Making
This work addresses the challenge of designing interpretable AI tools for human decision-makers in high-dimensional settings, providing theoretical and empirical insights into the trade-offs between computational tractability and robustness to human naivete.
The paper studies algorithms that highlight a small subset of case-specific features for human decision-makers, showing that optimizing for sophisticated agents is computationally intractable while optimizing for naive agents is tractable. It demonstrates that policies optimal for sophisticated agents can perform poorly with naive agents, and illustrates the framework using the American Housing Survey.
Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate all available information. In such settings, we study algorithms that highlight a small subset of case-specific features for human consideration, rather than producing a single prediction or recommendation. We model highlighting as a constrained information policy that selects a small number of features to reveal. A central issue is how humans interpret the algorithm's choice of features: a sophisticated agent correctly conditions on the selection rule, while a naive agent updates only on revealed feature values and treats the selection event as exogenous. We show that optimizing highlighting for sophisticated agents can be computationally intractable, even in simple discrete and binary settings, whereas optimizing for naive agents is tractable as long as the maximal bandwidth is fixed. We also show that a highlighting policy that is optimal for sophisticated agents can perform arbitrarily poorly when deployed to naive agents, motivating robust, implementable alternatives. We illustrate our framework in a calibrated empirical exercise based on the American Housing Survey. Overall, our results establish the value of highlighting a context-specific set of features rather than a fixed one as a practically appealing and computationally feasible tool for achieving human-algorithm complementarity.