Structuring Business Process Context Information for Process Monitoring and Prediction

Brunk Jens

Abstract

The advance of Big Data, the Internet of Things (IoT) and with it the integration of various systems - generally referred to as digitalization - provides huge amounts of data that can be leveraged by modern Business Process Management (BPM) methods. Predictive Process Monitoring (PPM) represents a novel branch of process mining, which deals with real-time analysis of currently running process instances and also with the prediction of its future behavior. Most of the early PPM techniques base their analyzes and predictions solely on the control-flow characteristic of a business process, i.e. the process events. Recently, researchers are attempting to incorporate additional process-related information, also known as the process context, into their predictive models. To use the available context information to full capacity, we require an understanding of the concept of business process context information. Based on both empirical and conceptual sources, we develop a taxonomy that provides a comprehensive overview of the characteristics of business process context information. This overview can then be leveraged, e.g. in process monitoring and prediction. Our taxonomy adds descriptive knowledge to the field of BPM, specifically PPM, and strengthens the conceptual foundation of context-sensitive process monitoring and prediction.

Keywords
Taxonomy, Business Process, Context, ContextSensitivity, Predictive Process Monitoring