Self-adjusting Recommendations for People-Driven Ad-Hoc Processes

A company’s ability to flexibly adapt to changing business requirements is one key factor to remain competitive. The required flexibility in peopledriven processes is usually achieved through ad-hoc workflows. E ective guidance in ad-hoc workflows requires simultaneous consideration of multiple goals: support of individual work habits, exploration of crowd process knowledge, and automatic adaptation to changes. This paper presents a self-adjusting approach for providing context-sensitive process recommendations based on the analysis of user behavior, crowd processes, and continuous application of process detection. Specifically, we classify users as eagles (i.e., specialists) or flock. The approach is evaluated in the context of the European research project Commius.