Efficient Selection of Process Mining Algorithms

While many process mining algorithms have been proposed recently, there does not exist a widely accepted benchmark to evaluate and compare these process mining algorithms. As a result, it can be difficult to choose a suitable process mining algorithm for a given enterprise or application domain. Some recent benchmark systems have been developed and proposed to address this issue. However, evaluating available process mining algorithms against a large set of business models (e.g., in a large enterprise) can be computationally expensive, tedious, and time-consuming. This paper investigates a scalable solution that can evaluate, compare, and rank these process mining algorithms efficiently, and hence proposes a novel framework that can efficiently select the process mining algorithms that are most suitable for a given model set. In particular, using our framework, only a portion of process models need empirical evaluation and others can be recommended directly via a regression model. As a further optimization, this paper also proposes a metric and technique to select high-quality reference models to derive an effective regression model. Experiments using artificial and real data sets show that our approach is practical and outperforms the traditional approach.