Algorithmic Feature Highlighting for Human-AI Decision-Making

2026-04-24

AI Summary

This study addresses the challenge of human decision-making in high-dimensional, complex environments where individuals cannot effectively process all available features. The authors propose a dynamic feature highlighting algorithm that, under limited cognitive bandwidth, presents only a small set of context-relevant features to support human judgment rather than directly providing predictive outputs. A key innovation lies in distinguishing two cognitive modes through which humans interpret the algorithm’s highlighting mechanism—sophisticated versus naive—and formally modeling their differences for the first time. Theoretical analysis demonstrates the intractability of optimizing for sophisticated agents, leading to the development of a computationally feasible and robust highlighting strategy tailored to naive agents. Combining constrained information policy modeling, discrete optimization, and Bayesian inference—and calibrated using U.S. Housing Survey data—the empirical results show that this dynamic highlighting approach significantly outperforms static feature sets and enhances human–AI collaborative decision performance.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Heuristic Search
• Machine Learning: Learning Preferences or Rankings

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

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.

Problem

• feature highlighting
• human-AI decision-making
• information selection
• cognitive bandwidth
• algorithmic assistance

Innovation

• feature highlighting
• human-AI collaboration
• information design
• cognitive heterogeneity
• computational tractability