Capturing the Complexity of Human Strategic Decision-Making with Machine Learning

TL;DR

This study uses a large dataset of human strategic decisions in matrix games to train neural networks, outperforming existing theories and revealing how game complexity influences human reasoning and decision-making.

Contribution

The paper introduces a large-scale dataset and a neural network model that predicts human strategic choices better than existing theories, and develops an interpretable model linking decision complexity to behavior.

Findings

Neural network outperforms traditional theories in predicting decisions.

Game complexity affects humans' ability to respond and reason.

Context-dependent behavior explains deviations from Nash equilibrium.

Abstract

Understanding how people behave in strategic settings--where they make decisions based on their expectations about the behavior of others--is a long-standing problem in the behavioral sciences. We conduct the largest study to date of strategic decision-making in the context of initial play in two-player matrix games, analyzing over 90,000 human decisions across more than 2,400 procedurally generated games that span a much wider space than previous datasets. We show that a deep neural network trained on these data predicts people's choices better than leading theories of strategic behavior, indicating that there is systematic variation that is not explained by those theories. We then modify the network to produce a new, interpretable behavioral model, revealing what the original network learned about people: their ability to optimally respond and their capacity to reason about others are dependent on the complexity of individual games. This context-dependence is critical in explaining deviations from the rational Nash equilibrium, response times, and uncertainty in strategic decisions. More broadly, our results demonstrate how machine learning can be applied beyond prediction to further help generate novel explanations of complex human behavior.