ProReco: A Process Discovery Recommender System
Tsung-Hao Huang, Tarek Junied, Marco Pegoraro, Wil M. P. van der Aalst
TL;DR
This work tackles the challenge of selecting an appropriate process discovery algorithm for a given event log by introducing ProReco, a Process Discovery Recommender System. ProReco combines an expanded feature pool with machine learning predictors (based on $xgboost$) to forecast quality measures ($$fitness, $$simplicity, $$precision, and $$generalization) and computes a weighted score using user-supplied weights $W$ for personalized recommendations. It uses 162 engineered features, including Direct-Follows Graph and footprint-based metrics, and is trained on real and synthetic logs; explanations are provided via SHAP values to foster transparency and trust. The system integrates with PM4Py, offers interactive visualization of discovered models, and outlines future work on parameter exploration, runtime considerations, and user studies to validate usability and efficacy.
Abstract
Process discovery aims to automatically derive process models from historical execution data (event logs). While various process discovery algorithms have been proposed in the last 25 years, there is no consensus on a dominating discovery algorithm. Selecting the most suitable discovery algorithm remains a challenge due to competing quality measures and diverse user requirements. Manually selecting the most suitable process discovery algorithm from a range of options for a given event log is a time-consuming and error-prone task. This paper introduces ProReco, a Process discovery Recommender system designed to recommend the most appropriate algorithm based on user preferences and event log characteristics. ProReco incorporates state-of-the-art discovery algorithms, extends the feature pools from previous work, and utilizes eXplainable AI (XAI) techniques to provide explanations for its recommendations.