Predicting and Understanding Initial Play

Drew Fudenberg and Annie Liang

American Economic Review, 2019, vol. 109, issue 12, 4112-41

Abstract: We use machine learning to uncover regularities in the initial play of matrix games. We first train a prediction algorithm on data from past experiments. Examining the games where our algorithm predicts correctly, but existing economic models don't, leads us to add a parameter to the best performing model that improves predictive accuracy. We then observe play in a collection of new "algorithmically generated" games, and learn that we can obtain even better predictions with a hybrid model that uses a decision tree to decide game-by-game which of two economic models to use for prediction.

JEL-codes: C70 C91 (search for similar items in EconPapers)
Date: 2019
Note: DOI: 10.1257/aer.20180654
References: Add references at CitEc
Citations: View citations in EconPapers (19)

Downloads: (external link)
https://www.aeaweb.org/doi/10.1257/aer.20180654 (application/pdf)
https://www.aeaweb.org/doi/10.1257/aer.20180654.data (application/zip)
https://www.aeaweb.org/doi/10.1257/aer.20180654.appx (application/pdf)
https://www.aeaweb.org/doi/10.1257/aer.20180654.ds (application/zip)
Access to full text is restricted to AEA members and institutional subscribers.

Related works:
Working Paper: Predicting and Understanding Initial Play (2018)
Working Paper: Predicting and Understanding Initial Play (2018)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aea:aecrev:v:109:y:2019:i:12:p:4112-41

Ordering information: This journal article can be ordered from
https://www.aeaweb.org/journals/subscriptions

Access Statistics for this article

American Economic Review is currently edited by Esther Duflo

More articles in American Economic Review from American Economic Association Contact information at EDIRC.
Bibliographic data for series maintained by Michael P. Albert ().