Probabilistic Online Action Prediction

Brian Davison and Haym Hirsh

People display regularities in almost everything they do. This paper proposes characteristics of an idealized algorithm that would allow a user interface to adapt to an individual’s pattern of use. We describe a simple predictive method with these characteristics and show its predictive accuracy on a large dataset of UNIX commands to be better than others that have been considered, while using fewer computational and memory resources.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.