Predicting and Understanding Human Action Decisions during Skillful Joint-Action via Machine Learning and Explainable-AI

Abstract

This study uses supervised machine learning (SML) and explainable artificial intelligence (AI) to model, predict and understand human decision-making during skillful joint-action. Long short-term memory networks were trained to predict the target selection decisions of expert and novice actors completing a dyadic herding task. Results revealed that the trained models were expertise specific and could not only accurately predict the target selection decisions of expert and novice herders but could do so at timescales that preceded an actor's conscious intent. To understand what differentiated the target selection decisions of expert and novice actors, we then employed the explainable-AI technique, SHapley Additive exPlanation, to identify the importance of informational features (variables) on model predictions. This analysis revealed that experts were more influenced by information about the state of their co-herders compared to novices. The utility of employing SML and explainable-AI techniques for investigating human decision-making is discussed.

Dynamical biomarkers in teams and other multiagent systems

“…35 This includes identifying what task information supports effective action decisions. [36][37][38] Recently, Auletta et al 39 have provided evidence suggesting that these challenges can be addressed using cutting-edge Supervised Machine Learning (SML), Long-Short Term Memory (LSTM) artificial neural networks, and explainable-AI (Artificial Intelligence) techniques. Specifically, the authors demonstrated how SML trained LSTM networks can not only be trained to predict the action decisions of individuals during team activity, but that an analysis of the resultant models using the explainable-AI technique, SHapley Additive exPlanation (SHAP), 40 can also identify and differentiate the sources of information that underlie the action decisions of expert and non-expert actors.…”