Feature recommendation for structural equation model discovery in process mining

Abstract Process mining techniques can help organizations to improve their operational processes. Organizations benefit from process in finding and amending the root causes of performance or compliance problems. Considering volume data number features captured by information system today’s companies, task discovering set that should be considered causal analysis quite involving. In this paper, we propose a method for (aggregated) with possible effect on problem. The is usually done applying machine learning technique gathered supporting To prevent mixing up correlation causation, which may happen because interpreting findings as causal, structural equation model used analysis. We have implemented proposed plugin ProM, evaluated it using real synthetic event logs. These experiments show validity effectiveness methods.