Predicting Sequences of User Actions

People display regularities in almost everything they do. This paper proposes characteristics of an idealized algorithm that, when applied to sequences of user actions, would allow a user interface to adapt over time 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 at least as good as others that have been considered, while using fewer computational and memory resources.

Presented at the AAAI-98/ICML'98 Workshop on Predicting the Future: AI Approaches to Time Series Analysis, Madison, WI, July 27, 1998 and published in Predicting the Future: AI Approaches to Time Series Problems, Technical Report WS-98-07, pp. 5-12, AAAI Press.

This is a slightly revised and extended version of Probabilistic Online Action Prediction.

Back to Brian Davison's publications