Capturing the complexity of human strategic decision-making with machine learning – Nature
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
Advertisement
Nature Human Behaviour (2025)
Strategic decision-making is a crucial component of human interaction. Here we conduct a large-scale study of strategic decision-making in the context of initial play in two-player matrix games, analysing 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 this dataset predicts human choices with greater accuracy than leading theories of strategic behaviour, revealing systematic variation unexplained by existing models. By modifying this network, we develop an interpretable behavioural model that uncovers key insights: individuals’ abilities to respond optimally and reason about others’ actions are highly context dependent, influenced by the complexity of the game matrices. Our findings illustrate the potential of machine learning as a tool for generating new theoretical insights into complex human behaviours.
This is a preview of subscription content, access via your institution
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
27,99 € / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
111,21 € per year
only 9,27 € per issue
Buy this article
Prices may be subject to local taxes which are calculated during checkout
The datasets generated and/or analysed are available at https://osf.io/xrvaw.
The code used to generate the results is available at https://osf.io/xrvaw.
McKelvey, R. D. & Palfrey, T. R. Quantal response equilibria for normal form games. Games Econ. Behav. 10, 6–38 (1995).
Article Google Scholar
Camerer, C. F. Behavioral Game Theory: Experiments in Strategic Interaction (Princeton University Press, 2011).
Gächter, S. Behavioral game theory. In Blackwell Handbook of Judgment and Decision Making (eds Koehler D. J. & Harvey, N.) 485–503 (Blackwell Publishing Ltd., 2004).
Weizsäcker, G. Ignoring the rationality of others: evidence from experimental normal-form games. Games Econ. Behav. 44, 145–171 (2003).
Article Google Scholar
McKelvey, R. D. & Palfrey, T. R. An experimental study of the centipede game. Econometrica 60, 803–836 (1992).
Article Google Scholar
Eyster, E. Errors in strategic reasoning. In Handbook of Behavioral Economics: Applications and Foundations (eds Bernheim, B. et al.) Vol. 2, 187–259 (North Holland, 2019).
Fehr, E. & Schmidt, K. M. A theory of fairness, competition, and cooperation. Quart. J. Econ. 114, 817–868 (1999)
Article Google Scholar
Fudenberg, D. & Liang, A. Predicting and understanding initial play. Am. Econ. Rev. 109, 4112–4141 (2019).
Article Google Scholar
Golman, R., Bhatia, S. & Kane, P. B. The dual accumulator model of strategic deliberation and decision making. Psychol. Rev. 127, 477–504 (2020).
Article PubMed Google Scholar
Wright, J. R. & Leyton-Brown, K. Predicting human behavior in unrepeated, simultaneous-move games. Games Econ. Behav. 106, 16–37 (2017).
Article Google Scholar
Robinson, D. & Goforth, D. The Topology of the 2×2 Games: A New Periodic Table (Routledge, 2005).
Camerer, C. F., Ho, T.-H. & Chong, J.-K. A cognitive hierarchy model of games. Quart. J. Econ. 119, 861–898 (2004).
Article Google Scholar
Crawford, V. P., Costa-Gomes, M. A. & Iriberri, N. Structural models of nonequilibrium strategic thinking: theory, evidence, and applications. J. Econ. Lit. 51, 5–62 (2013).
Article Google Scholar
Murnighan, J. K., Roth, A. E. & Schoumaker, F. Risk aversion in bargaining: an experimental study. J. Risk Uncertainty 1, 101–124 (1988).
Article Google Scholar
Fudenberg, D., Kleinberg, J., Liang, A. & Mullainathan, S. Measuring the completeness of economic models. J. Polit. Econ. 130, 956–990 (2022).
Article Google Scholar
Peterson, J. C., Bourgin, D. D., Agrawal, M., Reichman, D. & Griffiths, T. L. Using large-scale experiments and machine learning to discover theories of human decision-making. Science 372, 1209–1214 (2021).
Article CAS PubMed Google Scholar
Enke, B. & Shubatt, C. Quantifying lottery choice complexity. Preprint at https://doi.org/10.3386/w31677 (2023).
Dezfouli, A. et al. Disentangled behavioural representations. In Advances in Neural Information Processing Systems (eds Wallach, H. et al.) (2019).
Agrawal, M., Peterson, J. C. & Griffiths, T. L. Scaling up psychology via scientific regret minimization. Proc. Natl Acad. Sci. USA 117, 8825–8835 (2020).
Article CAS PubMed PubMed Central Google Scholar
Hartford, J., Wright, J. R. & Leyton-Brown, K. Deep learning for predicting human strategic behavior. In Advances in Neural Information Processing (eds Lee, D. et al) (2016).
Marchiori, D. & Warglien, M. Predicting human interactive learning by regret-driven neural networks. Science 319, 1111–1113 (2008).
Article CAS PubMed Google Scholar
Shubatt, C. & Yang, J. Similarity and comparison complexity. Preprint at https://arxiv.org/abs/2401.17578 (2024).
Chmura, T., Kube, S., Pitz, T. & Puppe, C. Testing (beliefs about) social preferences: evidence from an experimental coordination game. Econ. Lett. 88, 214–220 (2005).
Article Google Scholar
Bland, J. & Nikiforakis, N. Coordination with third-party externalities. Eur. Econ. Rev. 80, 1–15 (2015).
Article Google Scholar
Enke, B. & Graeber, T. Cognitive uncertainty. Quart. J. Econ. 138, 2021–2067 (2023).
Article Google Scholar
Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).
Google Scholar
Download references
This work and related results were made possible with the support of the NOMIS Foundation. We thank N. Chater and S. Li for helpful discussions.
Department of Computer Science, Princeton University, Princeton, NJ, USA
Jian-Qiao Zhu & Thomas L. Griffiths
Faculty of Computing and Data Science, Boston University, Boston, MA, USA
Joshua C. Peterson
Department of Economics, Harvard University, Cambridge, MA, USA
Benjamin Enke
National Bureau of Economic Research, Cambridge, MA, USA
Benjamin Enke
Department of Psychology, Princeton University, Princeton, NJ, USA
Thomas L. Griffiths
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
J.-Q.Z.: conceptualization, methodology, investigation, formal analysis, data curation, software, visualization, writing (original draft), and writing (reviewing and editing); J.C.P.: methodology, formal analysis, software, visualization, and writing (reviewing and editing); B.E.: conceptualization, methodology, formal analysis, supervision, validation, and writing (reviewing and editing); T.L.G.: conceptualization, methodology, formal analysis, supervision, validation, writing (reviewing and editing), resources, and funding acquisition.
Correspondence to Jian-Qiao Zhu.
The authors declare no competing interests.
Nature Human Behaviour thanks James (R) Bland and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Peer reviewer reports are available.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Sections A–F, Figs. 1–7, Tables 1–5 and References.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Reprints and permissions
Zhu, JQ., Peterson, J.C., Enke, B. et al. Capturing the complexity of human strategic decision-making with machine learning. Nat Hum Behav (2025). https://doi.org/10.1038/s41562-025-02230-5
Download citation
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41562-025-02230-5
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
Advertisement
Nature Human Behaviour (Nat Hum Behav)
ISSN 2397-3374 (online)
© 2025 Springer Nature Limited
Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.
