Abstract: As more and more event data become available, the practical relevance of data mining process is increasing. Process mining techniques aim to discover, monitor and improve real processes by extracting knowledge from event logs. A large volume of event data provides both opportunities and challenges for data mining process. The present process mining techniques have problems dealing with large event logs referring to many different activities. Therefore, we propose a generic approach to decompose process mining problems. It is possible to split computationally challenging process mining problems into many smaller problems that can be analyzed easily and whose results can be combined into solutions for the original problems. We present the matching algorithms to decompose the whole process model into several groups of traces and the numerical analysis of data mining models based on Stochastic Wellformed Workflow (SWWF).