Multi-perspective Comparison of Business Process Variants Based on Event Logs

Business Process Variant Analysis Based on Mutual Fingerprints of Event Logs

“…6). We note that the approach in [6] produces similar results, which we did not show due to lack of space. The baselines are unable to identify control-flow differences completely.…”

“…That said, as a side effect, sometimes the resulting fingerprints might contain a large number of edges. In contrast, the baselines [5,6] are unable to capture such correlation because the frequency of an edge is considered in their analysis. 6.…”

“…This work was later extended in [5], by inducting decision trees for performance data among process variants. Nguyen et al [6] encode process variants into Perspective Graphs. The comparison of perspective graphs results in a Differential Graph, which is a graph that contains common nodes and edges, and also nodes and edges that appear in one perspective graph only.…”

“…The problem is exacerbated by the fact that a directly-follows graph generalises process behavior since the combination of the various edges give rise to more paths than the traces in the event log. Indeed the baselines [5,6] consider only the edge's frequency, whereas our approach considers both frequency and location of an edge simultaneously. For example, the approach in [5] identifies that the frequency of (Create Fine, Payment) (the orange edge) is different between process variants.…”

“…event logs) recorded by information systems, is a common use case in process mining [4]. Existing techniques for process variant analysis [5,6] 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).…”