Wil van der Aalst
Process Mining: Making Sense of Processes Hidden in Big Event Data
The two most prominent process mining tasks are process discovery (i.e., learning a process model from an event log) and conformance checking (i.e., diagnosing and quantifying differences between observed and modeled behavior). The increasing availability of event data makes these tasks highly relevant for process analysis and improvement. Therefore, process mining is considered to be one of the key technologies for Business Process Management (BPM). In recent years, we have applied process mining in over 100 organizations. However, as event logs and process models grow, process mining becomes more challenging. Therefore, we propose a fully generic approach to decompose process mining problems into smaller problems that can be analyzed more efficiently. As shown, process discovery and conformance checking can be done per process fragment and the results can be aggregated. This has advantages in terms of efficiency and diagnostics. Moreover, in his talk prof. Van der Aalst will also show additional challenges and solutions approaches related to “Big Event Data”. For example, approaches for concept drift analysis and on-the-fly process mining will be sketched.