A Rule-Based Recommendation Approach for Business Process Modeling

Business process modeling is a crucial, yet time-consuming and knowledge-intensive task. This is particularly the case when modeling a domain-specific process, which often requires the use of highly specialized terminology in a consistent manner. To alleviate these issues, the process modeling task can be supported by techniques that suggest how a model under development can be expanded. In this work, we provide such suggestions through a rule-based activity recommendation approach, which suggests suitable activities to be included at a user-defined position in a process model. A benefit of our rule-based work over other approaches is that it accompanies recommendations with explanations, providing additional transparency and trustworthiness to users. Furthermore, through comprehensive evaluation experiments on a large set of real-world process models, we show that our rule-based approach outperforms other methods, including an embedding-based one.