Cognitive Model Priors for Predicting Human Decisions

Human decision-making underlies all economic behavior. For the past four decades, human decision-making under uncertainty has continued to be explained by theoretical models based on prospect theory, a framework that was awarded the Nobel Prize in Economic Sciences. However, theoretical models of this kind have developed slowly, and robust, high-precision predictive mod-els of human decisions remain a challenge. While machine learning is a natural candidate for solv-ing these problems, it is currently unclear to what extent it can improve predictions obtained by cur-rent theories. We argue that this is mainly due to data scarcity, since noisy human behavior re-quires massive sample sizes to be accurately cap-tured by off-the-shelf machine learning methods. To solve this problem, what is needed are ma-chine learning models with appropriate inductive biases for capturing human behavior, and larger datasets. We offer two contributions towards this end: first, we construct “cognitive model priors” by pretraining neural networks with synthetic data generated by cognitive models (i.e., theoretical models developed by cognitive psychologists). We find that fine-tuning these networks on small datasets of real human decisions results in un-precedented state-of-the-art improvements on two benchmark datasets. Second, we present the first large-scale dataset for human decision-making, containing over 240,000 human judgments across over 13,000 decision problems. This dataset re-veals the circumstances where cognitive model priors are useful, and provides a new standard for benchmarking prediction of human decisions under uncertainty.