Third party funded individual grant
Acronym: CoPPA
Start date : 01.01.2023
End date : 30.06.2025
The project described in this proposal is situated in the research stream of Business Process Management (BPM). It aims to explore how process analytics can be used by businesses to forecast future process behavior and how these predictive techniques from process analytics could leverage contextual information for better prediction performance. In particular, the goal of the project is to develop a context-aware predictive process monitoring approach that is based on probabilistic models from the field of Dynamic Bayesian Networks (DBN). The approach will be able to forecast what activity of a currently running process instance will be likely seen next. By including context information of a process, we seek to achieve a high prediction accuracy. We understand context as every aspect related to a business process that goes beyond the sheer name of an activity. Hence, context includes, for instance, input and output data of an activity, people performing an activity, and sensor data characterizing the environment of a process. Context can significantly influence the behavior of a process, so we can expect that being aware of what context has been present in a process in-stance can increase the prediction accuracy of a predictive process monitoring approach (e.g., the amount of a loan in a loan approval process may have a considerable influence onto the subsequent decisions made in the process and thus influences its behavior).