A composite machine-learning-based framework for supporting low-level event logs to high-level business process model activities mappings enhanced by flexible BPMN model translation

Process mining is an emerging discipline that aims to analyze business processes using event data logged by IT systems. In process mining, the focus is on how to effectively and efficiently predict the next process/trace to be activated among all the possible processes/traces that are available in the process schema (usually modeled as a graph). Most of the existing process mining techniques assume that there is a one-to-one mapping between process model activities and the events that are recorded during process execution. However, event logs and process model activities are at different level of granularity. In this paper, we present a machine-learning-based approach to map low-level event logs to high-level activities. With this work, we can bridge the abstraction levels when the high-level labels of the low-level events are not available. The proposed approach consists of two main phases: automatic labeling and machine-learning-based classification. In automatic labeling, a modified k-prototypes clustering approach has been used in order to obtain the labeled examples. Then, in the second phase, we trained different ML classifiers using the obtained labeled examples. Since, in real-life applications and systems, business processes are expressed according to the Business Process Model and Notation (BPMN) format, we improve our proposed framework by means of an innovative, flexible BPMN model translation methodology that acts at the first phase. We demonstrate the applicability of our proposed framework using two case studies with real-world event logs, and provide its experimental assessment and analysis.