A Classi cation Approach for Prediction of Target Events in Temporal Sequences

Learning to predict signiicant events from sequences of data with categorical features is an important problem in many application areas. We focus on events for system management, and formulate the problem of prediction as a classiication problem. We perform co-occurrence analysis of events by means of Singular Value Decomposition (SVD) of the examples constructed from the data. This process is combined with Support Vector Machine (SVM) classiication, to obtain eecient and accurate predictions. We conduct an analysis of statistical properties of event data, which explains why SVM classiication is suitable for such data, and perform an empirical study using real data.