Plonsky Ori, Apel Reut, Ert Eyal, Tennenholtz Moshe, Bourgin David, Peterson Joshua C, Reichman Daniel, Griffiths Thomas L, Russell Stuart J, Carter Even C, Cavanagh James F, Erev Ido
Technion - Israel Institute of Technology, Haifa, Israel.
The Hebrew University of Jerusalem, Jerusalem, Israel.
Nat Hum Behav. 2025 Jul 21. doi: 10.1038/s41562-025-02267-6.
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. Here we introduce BEAST gradient boosting (BEAST-GB), a hybrid model integrating behavioural 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 that BEAST-GB predicts more accurately than neural networks trained on extensive data and dozens of existing behavioural models. BEAST-GB also generalizes robustly across unseen experimental contexts, surpassing direct empirical generalization, and helps to refine and improve the behavioural theory itself. Our analyses highlight the potential of anchoring predictions on behavioural 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 behaviour.
预测人类在风险和不确定性下的决策仍然是跨学科的一项基本挑战。现有模型即使在诸如彩票选择等高度程式化的任务中也常常面临困难。在此，我们引入了BEAST梯度提升（BEAST-GB），这是一种将行为理论（BEAST）与机器学习相结合的混合模型。我们首先介绍了CPC18，这是一项预测风险选择的竞赛，BEAST-GB在其中获胜。然后，使用两个大型数据集，我们证明BEAST-GB的预测比在大量数据上训练的神经网络以及数十种现有的行为模型更准确。BEAST-GB还能在未见的实验情境中稳健泛化，超越直接的经验泛化，并有助于完善和改进行为理论本身。我们的分析突出了即使在数据丰富的环境中，甚至当理论本身表现不佳时，将预测锚定在行为理论上的潜力。我们的结果强调了将机器学习与理论框架相结合，尤其是像BEAST这样为预测而设计的框架，如何能够提高我们预测和理解人类行为的能力。
