Measuring the interestingness of temporal logic behavioral specifications in process mining

The assessment of behavioral rules with respect to a given dataset is key in several research areas, including declarative process mining, association rule and specification mining. An required check how well set discovered describes the input data, determine what extent data complies predefined rules. Particularly Support Confidence are used most often, yet they reportedly unable provide sufficiently rich feedback users cause representing coincidental behavior be deemed as representative for event logs. In addition, these measures designed work on rules, thus lacking generality extensibility. this paper, we address gap by developing measurement framework temporal based (LTLpf). suitable any expressed reactive form custom probabilistic interpretation such We show that our can seamlessly adapt well-known mining field Also, test software prototype implementing synthetic real-world investigate properties characterizing those context analysis.