On the Use of Log-Based Model Checking, Clustering and Machine Learning for Process Behavior Prediction

The paper proposes the use of Linear Temporal Logic (LTL) formulas for the behavioral description of the traces corresponding to log files. Such descriptions are used to group similar traces into classes applying standard clustering techniques. The classification results are used to feed a machine learning system able to predict, after a few initial events, the cluster to which an in-execution process is probably going to belong. The prediction model could be used to feed an on-line recommendation system so as to drive the process towards a desired cluster or to prevent it from being part of a non-desired one. The paper describes the used methodology and shows its validity by means of the application to a real log.