Predicting human decision making in psychological tasks with recurrent neural networks

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 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 the human subjects at each step of their decision making, 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 Prisoners Dilemma comprising 168,386 individual decisions and postprocess 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 from these published psychological experiments of human decision making, and demonstrate a clear advantage over the state-of-the-art methods in predicting human decision making trajectories in both single-agent scenarios such as the Iowa Gambling Task and multi-agent scenarios such as the Iterated Prisoners Dilemma. In the prediction, we observe that the weights of the top performers tends to have a wider distribution, and a bigger bias in the LSTM networks, which suggests possible interpretations for the distribution of strategies adopted by each group. Author summaryThe challenge of predicting human decision is important for many application domains like economy, marketing and artificial intelligence. But the domain where the human behavior modeling is especially crucial is psychology, where the goal is to describe, explain and predict these behaviors. Within this domain, creating agents that effectively mimic human decision making is particularly important. However, despite the many behavioral tasks and analytical methods developed to simulate the process of human decision making in real situations, there have not been a predictive model that can well predict the human decision making trajectories in these psychological tasks. In this predictive modeling problem, we propose to use the long short-term memory networks (LSTM), a popular recurrent neural network architecture and effectively predict the time series of the actions taken by the human subjects at each step of their decision making in both the Iowa Gambling Task, a single-agent game with monetary reward, and the Iterated Prisoners Dilemma, a complex multi-agent social game with non-monetary capital at stake. To the best of our knowledge, this is the first application of such methods in this research domain.