The quality of process mining results highly depends on the quality of the input data where noise, infrequent behaviors, log incompleteness or many different variants undercut the assumptions of process discovery algorithms, and lead to low-quality results. ProM provides numerous event log pre-processing and filtering options, but they require expert knowledge to understand when which pre-processing step is advised to reach a particular outcome. The objective of this assignment is to develop a comprehensive framework for event log pre-processing and a recommender that suggests the user adequate pre-processing steps depending on the data properties and the analysis task. Ideas are to be realized in a proof-of-concept implementation.
Contact: Dr. Dirk Fahland.