Public benchmark dataset for Conformance Checking in Process Mining
datasetposted on 2022-01-30, 09:34 authored by Daniel Reissner
This dataset contains a variety of publicly available real-life event logs. We derived two types of Petri nets for each event log with two state-of-the-art process miners : Inductive Miner (IM) and Split Miner (SM). Each event log-Petri net pair is intended for evaluating the scalability of existing conformance checking techniques.We used this data-set to evaluate the scalability of the S-Component approach for measuring fitness. The dataset contains tables of descriptive statistics of both process models and event logs. In addition, this dataset includes the results in terms of time performance measured in milliseconds for several approaches for both multi-threaded and single-threaded executions. Last, the dataset contains a cost-comparison of different approaches and reports on the degree of over-approximation of the S-Components approach. The description of the compared conformance checking techniques can be found here: https://arxiv.org/abs/1910.09767.
The dataset has been extended with the event logs of the BPIC18 and BPIC19 logs. BPIC19 is actually a collection of four different processes and thus was split into four event logs. For each of the additional five event logs, again, two process models have been mined with inductive and split miner. We used the extended dataset to test the scalability of our tandem repeats approach for measuring fitness. The dataset now contains updated tables of log and model statistics as well as tables of the conducted experiments measuring execution time and raw fitness cost of various fitness approaches. The description of the compared conformance checking techniques can be found here: https://arxiv.org/abs/2004.01781.
The dataset has also been used to measure the scalability of a new Generalization measure based on concurrent and repetitive patterns. : A concurrency oracle is used in tandem with partial orders to identify concurrent patterns in the log that are tested against parallel blocks in the process model. Tandem repeats are used with various trace reduction and extensions to define repetitive patterns in the log that are tested against loops in the process model. Each pattern is assigned a partial fulfillment. The generalization is then the average of pattern fulfillments weighted by the trace counts for which the patterns have been observed. The dataset no includes the time results and a breakdown of Generalization values for the dataset.