We are happy to report we have two accepted papers at the International conference in Business Process Management (BPM) 2024, taking place in Krakow, Poland.
These two papers were published in collaboration with the Eindhoven Technical University and Utrecht University.
1. Uncovering Patterns for Local Explanations in Outcome-based Predictive Process Monitoring
Authors: Andrei Buliga A., Mozhgan Vazifehdoostirani , Laura Genga, Xixi Lu, Remco Dijkman, Chiara Ghidini,Chiara Di Francescomarino, Hajo Reijers
Abstract: Explainable Predictive Process Monitoring aims at deriving explanations of the inner workings of black-box classifiers used to predict the continuation of ongoing process executions. Most existing techniques use data attributes (e.g., the loan amount) to explain the prediction outcomes. However, explanations based on control flow patterns (such as calling the customers first, and then validating the application, or providing early discounts) cannot be provided. This omission may result in many valuable, actionable explanations going undetected. To fill this gap, this paper proposes PABLO (PAttern Based LOcal Explanations), a framework that generates local control-flow aware explanations for a given predictive model. Given a process execution and its outcome prediction, PABLO discovers control-flow patterns from a set of alternative executions, which are used to deliver explanations that support or flip the prediction for the given process execution. Evaluation against real-life event logs shows that PABLO provides high-quality explanations of predictions in terms of fidelity and accurately explains the reasoning behind the predictions of the black box models. A qualitative comparison showcases how the patterns that PABLO derives can influence the
prediction outcome, aligned with the early findings from the literature.
2. Optimizing Resource Allocation Policies in Real-World Business Processes using Hybrid Process Simulation and Deep Reinforcement Learning
Authors: Francesca Meneghello, Jeroen Middelhuis, Massimiliano Ronzani, Laura Genga, Zaharah Bukhsh, Chiara Di Francescomarino, Chiara Ghidini and Remco Dijkman
Abstract:Resource allocation refers to the assignment of resources to activities for their execution within a business process at runtime. While resource allocation approaches are common in industries such as manufacturing, directly applying them to business processes remains a challenge. Recently, techniques like Deep Reinforcement Learning (DRL) have been used to learn efficient resource allocation strategies to minimize the cycle time. While DRL has been proven to work well for simplified synthetic processes, its usefulness in real-world business processes remains untested, partly due to the challenging nature of realizing accurate simulation environments. To overcome this limitation, we propose DRLHSM that combines DRL with Hybrid simulation models (HSM). The HSM can accurately replicate the business process behavior so that we can assess the effectiveness of DRL in optimizing real-world business processes. We evaluate our method on four real-world and two elaborate synthetic business processes, constrained by temporal resource availability and a restricted number of resources. An empirical evaluation shows that DRLHSM outperforms the benchmarks by, on average, 45%, up to 307%, in 14 out of 24 considered evaluation scenarios and is competitive with the best-performing benchmark in 8 scenarios.
