Explainable Predictive Process Monitoring
This work solves the problem of interpretability in predictive process monitoring for organizations, offering incremental improvements by applying existing explanation methods to a new domain.
The paper addresses the lack of explanation capabilities in predictive business process monitoring by using Shapley Values to provide robust explanations for predictions like remaining time or activity execution, demonstrating this approach on real-life benchmarks.
Predictive Business Process Monitoring is becoming an essential aid for organizations, providing online operational support of their processes. This paper tackles the fundamental problem of equipping predictive business process monitoring with explanation capabilities, so that not only the what but also the why is reported when predicting generic KPIs like remaining time, or activity execution. We use the game theory of Shapley Values to obtain robust explanations of the predictions. The approach has been implemented and tested on real-life benchmarks, showing for the first time how explanations can be given in the field of predictive business process monitoring.