An explainable decision support system for predictive process analytics. (April 2023)

• Record Type: Journal Article
• Authors: Galanti, Riccardo; de Leoni, Massimiliano; Monaro, Merylin; Navarin, Nicolò; Marazzi, Alan; Di Stasi, Brigida; Maldera, Stéphanie
• Is Part Of: Engineering applications of artificial intelligence. Volume 120(2023)
• Publication Date: 2023-04
• Subjects: Explainable AI -- Predictive business process analytics -- Decision support systems -- Machine learning -- Shapley values -- Process mining; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2023.105904
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Predictive Process Analytics is becoming an essential aid for organizations, providing online operational support of their processes. However, process stakeholders need to be provided with an explanation of the reasons why a given process execution is predicted to behave in a certain way. Otherwise, they will be unlikely to trust the predictive monitoring technology and, hence, adopt it. This paper proposes a predictive analytics framework that is also equipped with explanation capabilities based on the game theory of Shapley Values. The framework has been implemented in the IBM Process Mining suite and commercialized for business users. The framework has been tested on real-life event data to assess the quality of the predictions and the corresponding evaluations. In particular, a user evaluation has been performed in order to understand if the explanations provided by the system were intelligible to process stakeholders. Highlights: Predictive Business Process Monitoring provides online operational support. Explainability is a necessary condition to build trust in the predictive technology. Explainable AI framework needs to be validated with real end users. Deployment of an Explainable Predictive framework to provide process insights. Shapley values provide the importance of the factors influencing the prediction.