Predictive Monitoring of Business Process Execution Delays

Nowadays, organizations are becoming increasingly aware of the importance of better utilizing their knowledge assets and adopting a quality management model based on a process approach. This can be achieved by adopting a multidisciplinary approach that combines the fields of Knowledge Management, Business Process Management and Process Mining. Therefore, to improve their performance and increase their responsiveness, organizations must identify, manage and monitor all the business processes (BP) that are likely to mobilize crucial knowledge. In fact, implementing an IT system that automates business processes is necessary to achieve these goals. In this context, we propose a new method for predicting the execution times of business processes baptized BPETPM. This method is based on the CRISP-DM approach. We used a Process Mining techniques particularly the machine learning to exploit the execution data of a workflow engine. In order to prove the applicability of this method we have developed an intelligent system for predicting execution time of BP named iBPMS4PET. The applicative framework of this research work is the incoming mail management process as part of a group health insurance.