Predicting process performance: A white‐box approach based on process models. Issue 6 (27th March 2019)

• Record Type: Journal Article
• Authors: Verenich, Ilya; Dumas, Marlon; La Rosa, Marcello; Nguyen, Hoang
• Other Names: Raffo David guestEditor.; Bendraou Reda guestEditor.; Huang LiGuo guestEditor.; Maggi Fabrizio M. guestEditor.
• Is Part Of: Journal of software. Volume 31:Issue 6(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-03-27
• Subjects: explainable artificial intelligence -- flow analysis -- predictive process monitoring -- process mining -- transparent models; Software engineering -- Periodicals; Computer software -- Development -- Periodicals; Software maintenance -- Periodicals; 005.1
• DOI: 10.1002/smr.2170
• Languages: English
• ISSNs: 2047-7473

Abstract

Abstract: Predictive business process monitoring methods exploit historical process execution logs to provide predictions about running instances of a process. These predictions enable process workers and managers to preempt performance issues or compliance violations. A number of approaches have been proposed to predict quantitative process performance indicators for running instances of a process, including remaining cycle time, cost, or probability of deadline violation. However, these approaches adopt a black‐box approach, insofar as they predict a single scalar value without decomposing this prediction into more elementary components. In this paper, we propose a white‐box approach to predict performance indicators of running process instances. The key idea is to first predict the performance indicator at the level of activities and then to aggregate these predictions at the level of a process instance by means of flow analysis techniques. The paper develops this idea in the context of predicting the remaining cycle time of ongoing process instances. The proposed approach has been evaluated on real‐life event logs and compared against several baselines. Abstract : We propose an explainable predictive process monitoring method by extracting a BPMN process model from the event log, predicting a performance indicator at the level of activities, and then aggregating these predictions at the level of the whole process via flow analysis techniques. The paper develops this idea in the context of predicting the remaining execution time of ongoing process instances, by decomposing it into the predicted execution time of each activity that is to be executed.