Prediction and Discovery of Users ’ Desktop Behavior

We investigate prediction and discovery of user desktop activities. The techniques we explore are unsupervised. In the first part of the paper, we show that efficient many-class learning can perform well for action predic-tion in the Unix domain, significantly improving over previously published results. This finding is promis-ing for various human-computer interaction scenarios where rich predictive features of different types may be available and where there can be substantial nonsta-tionarity. In the second part, we briefly explore tech-niques for extracting salient activity patterns or motifs. Such motifs are useful in obtaining insights into user be-havior, automated discovery of (often interleaved) high-level tasks, and activity tracking and prediction.