Predictive process monitoring [1] aims at predicting the future of an ongoing process execution by learning from past historical business process executions. Diferent, often Machine Learning based, approaches have been proposed in the literature in order to provide predictions on the outcome, the remaining time, the required resources as well as the remaining activities of an ongoing execution, by leveraging information related to the control flow, the data flow, or even unstructured text contained in event logs, recording information about process executions. Together with the impressive growth of this young filed several challenges remain, ofter related to the multi-perspective nature of Business Process execution data. Important examples are: the inclusion of a-priori knowledge in a prediction [2], the ability to capture and exploit rich temporal relationships between diferent features, the explainability of the prediction and the predictive model for this type of data [3, 4], and even more crucially the ability to provide prescriptive [5] and actionable [6] predictions. In this talk I outline the work that was carried out in the Process & Data Intelligence research unit of Fondazione Bruno Kessler in the last 5 years, as well as ongoing future research directions, related to the challenges above. [1] C. Di Francescomarino, C. Ghidini, Predictive process monitoring, in: Process Mining Handbook, volume 448 of LNBIP, Springer, 2022, pp. 320-346. [2] C. Di Francescomarino, C. Ghidini, F. M. Maggi, G. Petrucci, A. Yeshchenko, An eye into the future: Leveraging a-priori knowledge in predictive business process monitoring, in: Business Process Management - 15th International Conference, BPM 2017, Proceedings, volume 10445 of LNCS, Springer, 2017, pp. 252-268. [3] R. Galanti, B. Coma-Puig, M. de Leoni, J. Carmona, N. Navarin, Explainable predictive process monitoring, in: 2nd International Conference on Process Mining, ICPM 2020, IEEE, 2020, pp. 1-8. [4] W. Rizzi, C. Di Francescomarino, F. M. Maggi, Explainability in predictive process monitoring: When understanding helps improving, in: BPM Forum 2020, Proceedings, volume 392 of LNBIP, Springer, 2020, pp. 141-158.
[5] S. A. Fahrenkrog-Petersen, N. Tax, I. Teinemaa, M. Dumas, M. de Leoni, F. M. Maggi, M. Weidlich, Fire now, fire later: alarm-based systems for prescriptive process monitoring, Knowl. Inf. Syst. 64 (2022) 559–587. [6] S. Branchi, ChiaraDi Francescomarino, C. Ghidini, D. Massimo, F. Ricci, M. Ronzani, Learning to act: a reinforcement learning approach to recommend the best next activities, BPM Forum 2022, Proceedings, 2022. To Appear.