Abstract We investigate prediction of users’ desktop activities in the Unix domain. The learning techniques we explore do not require explicit user teaching. We show that simple effificient many-class learning can perform well for action prediction, signififi- cantly improving over previously published results and baselines. This fifinding is promising for various human-computer interaction scenarios where a rich set of potentially predictive features is available, where there can be many different actions to predict, and where there can be considerable nonstationarity