Modelling and Predictive Monitoring of Business Processes under Uncertainty with Reinforcement Learning

Abstract

'Georgia Theodoropoulou' 'Georgios Miaoulis' 'Djamchid Ghazanfarpour' 'Alberto Cano' 'Sylvio Barbon Junior'] The analysis of business processes based on their observed behavior recorded in event logs can be performed with process mining. This method can discover, monitor, and improve processes in various application domains. However, the process models produced by typical process discovery methods are difficult for humans to understand due to their high complexity (the so-called “spaghetti-like” process models). Moreover, these methods cannot handle uncertainty or perform predictions because of their deterministic nature. Recently, researchers have been developing predictive approaches for running business cases of processes. This paper focuses on developing a predictive business process monitoring approach using reinforcement learning (RL), which has been successful in other contexts but not yet explored in this area. The proposed approach is evaluated in the banking sector through a use case.