Predicting human decision making in psychological tasks with recurrent neural networks

TL;DR

This paper introduces a novel application of LSTM recurrent neural networks to predict human decision-making in psychological tasks, leveraging extensive behavioral data and outperforming existing methods.

Contribution

It is the first to apply LSTM networks to model and predict human decisions in complex psychological tasks like the Prisoner's Dilemma and Iowa Gambling Task.

Findings

LSTM models outperform state-of-the-art prediction methods.

Behavioral data from multiple studies were effectively used for training.

Network weight distributions correlate with performance levels.

Abstract

Unlike traditional time series, the action sequences of human decision making usually involve many cognitive processes such as beliefs, desires, intentions, and theory of mind, i.e., what others are thinking. This makes predicting human decision-making challenging to be treated agnostically to the underlying psychological mechanisms. We propose here to use a recurrent neural network architecture based on long short-term memory networks (LSTM) to predict the time series of the actions taken by human subjects engaged in gaming activity, the first application of such methods in this research domain. In this study, we collate the human data from 8 published literature of the Iterated Prisoner's Dilemma comprising 168,386 individual decisions and post-process them into 8,257 behavioral trajectories of 9 actions each for both players. Similarly, we collate 617 trajectories of 95 actions from 10 different published studies of Iowa Gambling Task experiments with healthy human subjects. We train our prediction networks on the behavioral data and demonstrate a clear advantage over the state-of-the-art methods in predicting human decision-making trajectories in both the single-agent scenario of the Iowa Gambling Task and the multi-agent scenario of the Iterated Prisoner's Dilemma. Moreover, we observe that the weights of the LSTM networks modeling the top performers tend to have a wider distribution compared to poor performers, as well as a larger bias, which suggest possible interpretations for the distribution of strategies adopted by each group.