preCEP: facilitating predictive event-driven process analytics

  • Authors:
  • Bernd Schwegmann;Martin Matzner;Christian Janiesch

  • Affiliations:
  • ERCIS, University of Münster, Muenster, Germany;ERCIS, University of Münster, Muenster, Germany;AIFB, Karlsruhe Institute of Technology, Karlsruhe, Germany

  • Venue:
  • DESRIST'13 Proceedings of the 8th international conference on Design Science at the Intersection of Physical and Virtual Design
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The earlier critical decision can be made, the more business value can be retained or even earned. The goal of this research is to reduce a decision maker's action distance to the observation of critical events. We report on the development of the software tool preCEP that facilitates predictive event-driven process analytics (edPA). The tool enriches business activity monitoring with prediction capabilities. It is implemented by using complex event processing technology (CEP). The prediction component is trained with event log data of completed process instances. The knowledge obtained from this training, combined with event data of running process instances, allows for making predictions at intermediate execution stages on a currently running process instance's future behavior and on process metrics. preCEP comprises a learning component, a run-time environment as well as a modeling environment, and a visualization component of the predictions.