AI & Fundamentals

Predicting human decisions with behavioral theories and machine learning - Ori Plonsky, Assistant Professor, Technion-Israel Institute of Technology

Abstract:

Predicting human decision-making under risk and uncertainty remains a core challenge in economics, psychology, and related fields. Despite decades of research, no existing model consistently predicts even simple choices, such as selecting between lotteries. Here, we introduce BEAST Gradient Boosting (BEAST-GB), a novel hybrid approach that fuses a theory-driven behavioral model (BEAST) with state-of-the-art machine learning techniques. First, we demonstrate its success in CPC18, an open competition aimed at forecasting human choice behavior, which BEAST-GB won. Second, we show that BEAST-GB achieves state-of-the-art predictive accuracy on the largest publicly available dataset of risky decision-making, surpassing purely data-driven neural networks. This outcome highlights how theoretical insights retain their value even in the era of big data. Third, we provide evidence that BEAST-GB outperforms the original BEAST model across a variety of diverse choice datasets, illustrating the indispensable role of machine learning in capturing complex, idiosyncratic behavioral patterns. Finally, we confirm that BEAST-GB generalizes robustly to new experimental contexts outside its training domain. Taken together, these results underscore that uniting theory-rich frameworks with machine learning not only advances predictive performance but also offers a richer understanding of human choice.

Bio:

Ori Plonsky is an Assistant Professor in the Faculty of Data and Decision Sciences at the Technion-Israel Institute of Technology. His research spans behavioral decision-making, human learning, and the integration of data science with behavioral science, focusing on human choice prediction and computational modeling of behavior. Ori holds a PhD in Behavioral Sciences and has an engineering background, enhancing his interdisciplinary approach. His work has been published in journals such as Psychological Review, Nature Human Behavior, and PNAS. In 2022, he received the Hillel Einhorn New Investigator Award from the Society for Judgment and Decision Making. Beyond academia, Ori is a dedicated family man and avid supporter of Arsenal FC.