User Assistance during Process Execution - An Experimental Evaluation of Recommendation Strategies

In today's changing business environment, flexible Process-aware Information Systems (PAISs) are required to allow companies to rapidly adjust their business processes to changes in the environment. However, increasing flexibility poses additional challenges to the users of flexible PAISs and thus requires intelligent user assistance. To address this challenge we have previously proposed a recommendation service for supporting users during process execution by providing recommendations on possible next steps. Recommendations are generated based on similar past process executions considering the performance goal of the supported process. This paper follows up on this work and suggests additional strategies for generating recommendations. In addition, as major contribution of this paper, we investigate how effectively the recommendation strategies work for different processes and logs of different quality.