Saved in:
Bibliographic Details
Main Authors: Plonsky, Ori, Apel, Reut, Ert, Eyal, Tennenholtz, Moshe, Bourgin, David, Peterson, Joshua C., Reichman, Daniel, Griffiths, Thomas L., Russell, Stuart J., Carter, Evan C., Cavanagh, James F., Erev, Ido
Format: Preprint
Published: 2019
Subjects:
Online Access:https://arxiv.org/abs/1904.06866
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915411309625344
author Plonsky, Ori
Apel, Reut
Ert, Eyal
Tennenholtz, Moshe
Bourgin, David
Peterson, Joshua C.
Reichman, Daniel
Griffiths, Thomas L.
Russell, Stuart J.
Carter, Evan C.
Cavanagh, James F.
Erev, Ido
author_facet Plonsky, Ori
Apel, Reut
Ert, Eyal
Tennenholtz, Moshe
Bourgin, David
Peterson, Joshua C.
Reichman, Daniel
Griffiths, Thomas L.
Russell, Stuart J.
Carter, Evan C.
Cavanagh, James F.
Erev, Ido
contents Predicting human decisions under risk and uncertainty remains a fundamental challenge across disciplines. Existing models often struggle even in highly stylized tasks like choice between lotteries. We introduce BEAST Gradient Boosting (BEAST-GB), a hybrid model integrating behavioral theory (BEAST) with machine learning. We first present CPC18, a competition for predicting risky choice, in which BEAST-GB won. Then, using two large datasets, we demonstrate BEAST-GB predicts more accurately than neural networks trained on extensive data and dozens of existing behavioral models. BEAST-GB also generalizes robustly across unseen experimental contexts, surpassing direct empirical generalization, and helps refine and improve the behavioral theory itself. Our analyses highlight the potential of anchoring predictions on behavioral theory even in data-rich settings and even when the theory alone falters. Our results underscore how integrating machine learning with theoretical frameworks, especially those-like BEAST-designed for prediction, can improve our ability to predict and understand human behavior.
format Preprint
id arxiv_https___arxiv_org_abs_1904_06866
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Predicting human decisions with behavioral theories and machine learning
Plonsky, Ori
Apel, Reut
Ert, Eyal
Tennenholtz, Moshe
Bourgin, David
Peterson, Joshua C.
Reichman, Daniel
Griffiths, Thomas L.
Russell, Stuart J.
Carter, Evan C.
Cavanagh, James F.
Erev, Ido
Artificial Intelligence
Computer Science and Game Theory
Machine Learning
Predicting human decisions under risk and uncertainty remains a fundamental challenge across disciplines. Existing models often struggle even in highly stylized tasks like choice between lotteries. We introduce BEAST Gradient Boosting (BEAST-GB), a hybrid model integrating behavioral theory (BEAST) with machine learning. We first present CPC18, a competition for predicting risky choice, in which BEAST-GB won. Then, using two large datasets, we demonstrate BEAST-GB predicts more accurately than neural networks trained on extensive data and dozens of existing behavioral models. BEAST-GB also generalizes robustly across unseen experimental contexts, surpassing direct empirical generalization, and helps refine and improve the behavioral theory itself. Our analyses highlight the potential of anchoring predictions on behavioral theory even in data-rich settings and even when the theory alone falters. Our results underscore how integrating machine learning with theoretical frameworks, especially those-like BEAST-designed for prediction, can improve our ability to predict and understand human behavior.
title Predicting human decisions with behavioral theories and machine learning
topic Artificial Intelligence
Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/1904.06866