Predicting human decisions with behavioral theories and machine learning

Understand

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.