Utilizing domain knowledge in data-driven process discovery

Process mining aims to improve operational processes in a data-driven manner. To this end, process mining offers methods and techniques for systematically analyzing event data. These data are generated during the execution of processes and stored in organizations' information systems. Process discovery, a key discipline in process mining, comprises techniques used to (automatically) learn a process model from event data. However, existing algorithms typically provide low-quality models from real-life event data due to data-quality issues and incompletely captured process behavior. Automated filtering of event data is valuable in obtaining better process models. At the same time, it is often too rigorous, i.e., it also removes valuable and correct data. In many cases, prior knowledge about the process under investigation can be additionally used for process discovery besides event data. Therefore, a new family of discovery algorithms has been developed that utilizes domain knowledge about the process in addition to event data. To organize this research, we present a literature review of process discovery approaches exploiting domain knowledge. We define a taxonomy that systematically classifies and compares existing approaches. Finally, we identify remaining challenges for future work.