Business Process Variant Analysis based on Mutual Fingerprints of Event Logs
This addresses the issue of proliferating low-level differences in process mining for business analysts, though it is incremental as it builds on existing variant analysis techniques.
The paper tackles the problem of detecting statistically-significant differences between business process variants at the trace level, rather than at the granular level of individual activities, using a mutual fingerprint technique based on discrete wavelet transformation. The results show that this approach reveals differences that baselines miss or detects spurious differences in real-life event logs.
Comparing business process variants using event logs is a common use case in process mining. Existing techniques for process variant analysis detect statistically-significant differences between variants at the level of individual entities (such as process activities) and their relationships (e.g. directly-follows relations between activities). This may lead to a proliferation of differences due to the low level of granularity in which such differences are captured. This paper presents a novel approach to detect statistically-significant differences between variants at the level of entire process traces (i.e. sequences of directly-follows relations). The cornerstone of this approach is a technique to learn a directly follows graph called mutual fingerprint from the event logs of the two variants. A mutual fingerprint is a lossless encoding of a set of traces and their duration using discrete wavelet transformation. This structure facilitates the understanding of statistical differences along the control-flow and performance dimensions. The approach has been evaluated using real-life event logs against two baselines. The results show that at a trace level, the baselines cannot always reveal the differences discovered by our approach, or can detect spurious differences.