A Data-driven Process Recommender Framework
Sen Yang (Rutgers University);Xin Dong (Rutgers University);Leilei Sun (Dalian University of Technology);Yichen Zhou (Rutgers University);Richard A. Farneth (Children's National Medical Center);Hui Xiong (Rutgers University);Randall S. Burd (Children's National Medical Center);Ivan Marsic (Rutgers University)
Abstract
We present an approach for improving the performance of complex knowledge-based processes by providing data-driven step-by-step recommendations. Our framework uses the associations between similar historic process performances and contextual information to determine the established procedures. We introduce a novel similarity metric for grouping traces into clusters that incorporates temporal information about activity performance and handles concurrent activities. Our data-driven recommender system selects the appropriate prototype performance of the process based on user-provided context attributes. Our approach for determining the prototypes discovers the commonly performed activities and their temporal relationships. We tested our system on data from three real-world medical processes and achieved recommendation accuracy up to 0.77 F1 score (compared to 0.37 F1 score using ZeroR) and 63.2% of recommended procedures lie within the first five neighbors of the actual historic procedures in a set of 87 cases. Our framework works as an interactive visual analytic tool for process mining. This work shows the feasibility of data-driven decision support system for complex knowledge-based processes.
