On improving application utility prediction.

When using the computer, each user has some notion that "these applications are important" at a given point in time. We term this subset of applications that the user values as high-utility applications. Identifying these high-utility applications is critical to the fields of Task Analysis, User Interruptions, Workflow Analysis, and Goal Prediction. Yet, existing techniques to identify high-utility applications are based upon task identification, conglomeration of related windows, limited qualitative observation, or common sense. Our work directly associates measurable computer interaction (CPU consumption, window area, etc.) with the user's perceived application utility. In this paper, we present an objective utility function that accurately predicts the user's subjective impressions of application importance. Our work is based upon 321 hours of real-world data from 22 users (both professional and academic) improving existing techniques by over 53%.