Business process simulation is a well-known approach to estimate the impact of changes to a process with respect to time and cost measures – a practice known as what-if process analysis. The usefulness of such estimations hinges on the accuracy of the underlying simulation model. Data-Driven Simulation (DDS) methods leverage process mining techniques to learn business process simulation models from event logs. Empirical studies have shown that, while DDS models adequately capture the observed sequences of activities and their frequencies, they fail to accurately capture the temporal dynamics of real-life processes. In contrast, generative Deep Learning (DL) models are better able to capture such temporal dynamics. The drawback of DL models is that users cannot alter them for what-if analysis due to their black-box nature. This paper presents a hybrid approach to learn process simulation models from event logs wherein a (stochastic) process model is extracted via DDS techniques, and then combined with a DL model to generate timestamped event sequences. The proposed approach allows us to simulate different types of changes, including the addition of new activity types to a process. This latter capability is achieved by encoding the activities by means of embeddings, rather than representing them as one-hot-encoded categories. An experimental evaluation shows that the resulting hybrid simulation models match the temporal accuracy of pure DL models, while partially retaining the what-if analysis capability of DDS approaches. The evaluation also sheds light into the relative performance of multiple embedding approaches to represent the activities.

Abstract Business process simulation is a well-known approach to estimate the impact of changes to a process with respect to time and cost measures – a practice known as what-if process analysis. The usefulness of such estimations hinges on the accuracy of the underlying simulation model. Data-Driven Simulation (DDS) methods leverage process mining techniques to learn process simulation models from event logs. Empirical studies have shown that, while DDS models adequately capture the observed sequences of activities and their frequencies, they fail to accurately capture the temporal dynamics of real-life processes. In contrast, generative Deep Learning (DL) models are better able to capture such temporal dynamics. The drawback of DL models is that users cannot alter them for what-if analysis due to their black-box nature. This paper presents a hybrid approach to learn process simulation models from event logs wherein a (stochastic) process model is extracted via DDS techniques, and then combined with a DL model to generate timestamped event sequences. An experimental evaluation shows that the resulting hybrid simulation models match the temporal accuracy of pure DL models, while partially retaining the what-if analysis capability of DDS approaches.

Workflow monitoring and analysis concerns aim at identifying potential improvements of workflow applications. This paper presents an approach to specify and implement monitoring and analysis concerns on workflow applications raising the level of abstraction for workflow analysts. First, the specification of monitoring and analysis concerns is declared in a technology-independent way with a domain-specific language named MonitA. MonitA makes extensive use of the data available in the workflow application and its constituents to enhance the monitoring and analysis specifications. Second, we defined and implemented a strategy to assist developers to enhance a given workflow technology to support the generation of the monitoring and analysis code and its composition with the workflow application. This instrumentation-based approach enables the monitoring and analysis of workflow applications during their operational execution. We illustrate the flexibility of our approach by targeting different workflow platforms and different workflow applications.