Predicting Human Decisions with Behavioral Theories and Machine Learning
Abstract
Accurately predicting human decision-making under risk and uncertainty is a long-standing challenge in behavioral science and AI. We introduce BEAST Gradient Boosting (BEAST-GB), a hybrid model integrating behavioral insights derived from a behavioral model, BEAST, as features in a machine learning algorithm. BEAST-GB won CPC18, an open choice prediction competition, and outperforms deep learning models on large datasets. It demonstrates strong predictive accuracy and generalization across experimental contexts, highlighting the value of integrating domain-specific behavioral theories with machine learning to enhance prediction of human choices.
Cite
Text
Plonsky et al. "Predicting Human Decisions with Behavioral Theories and Machine Learning." NeurIPS 2024 Workshops: Behavioral_ML, 2024.Markdown
[Plonsky et al. "Predicting Human Decisions with Behavioral Theories and Machine Learning." NeurIPS 2024 Workshops: Behavioral_ML, 2024.](https://mlanthology.org/neuripsw/2024/plonsky2024neuripsw-predicting/)BibTeX
@inproceedings{plonsky2024neuripsw-predicting,
title = {{Predicting Human Decisions with Behavioral Theories and Machine Learning}},
author = {Plonsky, Ori and Apel, Reut and Ert, Eyal and Tennenholtz, Moshe and Bourgin, David and Peterson, Joshua and Reichman, Daniel and Griffiths, Thomas L. and Russell, Stuart and Carter, Evan and Cavanagh, James F. and Erev, Ido},
booktitle = {NeurIPS 2024 Workshops: Behavioral_ML},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/plonsky2024neuripsw-predicting/}
}