Towards Ex Ante Prediction of User Performance: A Novel NeuroIS Methodology Based on Real-Time Measurement of Mental Effort

Abstract

We propose a methodology of an ex ante prediction of users' performance based on analyzing the pupillary diameter variability captured by ordinary eye-tracking systems. Based on a realistic large-scale experimental evaluation of our methodology we show promising results that pave the way for a dynamic real-time adaption of IT to the user's mental effort and the expected user performance. Our non-invasive contact-free methodology can be applied cost-efficiently both in research and practical environments, without disturbing the participant/user.