What do machines learn, and why? To answer these questions we import models of human cognition into machine learning. We propose two ways of modeling machine learners based on this join: feasibility-based and cost-based machine learning. We evaluate and estimate our models using a deep learning...

The central question we address in this paper is: what can an analyst infer from choice data about what a decision maker has learned? The key constraint we impose, which is shared across models of Bayesian learning, is that any learning must be rationalizable. To implement this constraint, we...

We introduce a rational choice theory that allows for many forms of imperfect perception, including failures of memory, selective attention, and adherence to simplifying rules of thumb. Despite its generality, the theory has strong, simple, and intuitive implications for standard choice data and...

When choice options are complex, policy makers may seek to reduce decision making errors by making a high quality option the default. We show that this positive effect is at risk because such a policy creates incentives for decision makers to "drop out" by paying no attention to the decision and...

Consumers often face an overwhelming amount of information when deciding between products, and one of the primary policymaking tools available to improve their informativeness is the framing of this information. We introduce a general theoretical approach that characterizes when one frame is...