Automatic classification of event logs sequences for failure detection in WfM/BPM systems

Process mining is a technical alternative focused on solving some of the difficulties presented when modeling business processes, particularly when Business Process Management (BPM) systems present inconsistencies with the real process. Currently, there is an increasing interest in predicting the behavior of active work items in any business process, which would make possible to monitor the behavior of such processes in a more accurate way. Given the complexity of current business processes, conventional techniques are not always effective in addressing this type of requirements; therefore, machine learning techniques are being increasingly more used for this task. This work deals with the problem of fail detection in a BPM system from event logs, based on machine learning methods. The paper explores the use of two structural learning models, Hidden Markov Models (HMM) and Hidden semi-Markov models (HSMM). Both models are suitable to model sequence data, but the last one can take into consideration the duration time that the underlying process remains in one state. The experiments are carried out using a real database of about 460,000 event logs sequences. The results show that for the given dataset, fail detection can be achieved with an accuracy of 86.70% using the HSMM model. In order to reduce the computational load of the proposed approach, the models were implemented in a distributed processing environment using Apache Spark, which guarantees the scalability of the solution.