NEWS

  • Our paper on CH4I-PM project in KI!
    It’ out! Ronzani, M., Sulis, E. Improve Hospital Management Through Process Mining, Optimization, and Simulation: the CH4I-PM Project. Künstl Intell (2024). https://doi.org/10.1007/s13218-024-00882-5 Abstract: The growing digitalization of society opens up the exploitation of new IT techniques in the healthcare sector. This report presents an application of AI techniques such as prediction, optimization, and automated knowledge extraction with process mining from hospital information system data. In addition, a simulation effort with Building Information Modeling and Agent-Based Modeling techniques has been performed. The present report describes practical cases and the lesson learned from planning, management, and coordination activities of the project as a whole.
  • A paper on counterfactual explanation generation accepted at AAAI25
    The paper Generating Counterfactual Explanations Under Temporal Constraints by Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini, Marco Montali and Massimiliano Ronzani has been accepted for presentation at the main technical session at AAAI 2025! Abstract: Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods do not readily apply to temporal domains, such as that of process mining, where data take the form of traces of activities that must obey to temporal background knowledge expressing which dynamics are possible and which not. Specifically, counterfactuals generated off-the-shelf may violate the background knowledge, leading to inconsistent explanations. This work tackles this challenge by introducing a novel ap proach for generating temporally constrained counterfactuals, guaranteed to comply by design with background knowledge expressed in Linear Temporal Logic on process traces (LTLp). We do so by infusing automata-theoretic techniques for LTLp inside a genetic algorithm for counterfactual generation. The empirical evaluation shows that the generated counterfactuals are temporally meaningful and more interpretable for applications involving temporal dependencies.
  • Our Paper on Robust Scheduling in ITOR!
    It’ out!  Cunzolo, M.D., Ronzani, M., Aringhieri, R., Francescomarino, C.D., Ghidini, C., Guastalla, A. and Sulis, E. , Robust solutions via optimisation and predictive process monitoring for the scheduling of the interventional radiology procedures. Intl. Trans. in Op. Res. (2024). https://doi.org/10.1111/itor.13584 Abstract: Interventional radiology (IR) is an increasingly used medical specialty relying on the possibilities offered by medical imaging guidance technologies to perform minimally invasive procedures (both diagnostic and therapeutic) through very small incisions or body orifices. Although the operative context is quite similar to that of the classical operating room (OR) literature, to the best of our knowledge management problems arising in the IR operative context never appeared in the healthcare management literature. This is even more true for studies that combine the OR approach with automatic extraction of information from real hospital health record data as in the present study. Two specific features characterise our case study with respect to the traditional OR literature: due to the Italian legislation, the anaesthetist (usually in a very limited number) must be present for the entire duration of the procedure (C⁢1), and the IR does not have its own ward but receives inpatients from different wards (C⁢2). The aim of this paper is to introduce a novel approach to determine a robust solution for our case study problem addressing both features C⁢1 and C⁢2. Our approach is based on the interplay between optimisation and predictive process monitoring (PPM) models. The obtained results show that the proposed approach produces schedules that achieve higher usage rate, lower overtime and more patients operated on than the original schedule. We also show that the integration of PPM models within the optimisation workflow improves the quality of the output schedule with respect to the standard one-shot optimisation.
  • Our paper on hybrid business process simulation in Information Systems!
    It’ out! Francesca Meneghello, Chiara Di Francescomarino, Chiara Ghidini, Massimiliano Ronzani, Runtime integration of machine learning and simulation for business processes: Time and decision mining predictions, Information Systems, Volume 128, 2025, 102472, ISSN 0306-4379, https://doi.org/10.1016/j.is.2024.102472. Abstract: Recent research in Computer Science has investigated the use of Deep Learning (DL) techniques to complement outcomes or decisions within a Discrete Event Simulation (DES) model. The main idea of this combination is to maintain a white box simulation model complement it with information provided by DL models to overcome the unrealistic or oversimplified assumptions of traditional DESs. State-of-the-art techniques in BPM combine Deep Learning and Discrete Event Simulation in a post-integration fashion: first an entire simulation is performed, and then a DL model is used to add waiting times and processing times to the events produced by the simulation model. In this paper, we aim at taking a step further by introducing Rims (Runtime Integration of Machine Learning and Simulation). Instead of complementing the outcome of a complete simulation with the results of predictions a posteriori, Rims provides a tight integration of the predictions of the DL model at runtime during the simulation. This runtime-integration enables us to fully exploit the specific predictions while respecting simulation execution, thus enhancing the performance of the overall system both w.r.t. the single techniques (Business Process Simulation and DL) separately and the post-integration approach. In particular, the runtime integration ensures the accuracy of intercase features for time prediction, such as the number of ongoing traces at a given time, by calculating them during directly the simulation, where all traces are executed in parallel. Additionally, it allows for the incorporation of online queue information in the DL model and enables the integration of other predictive models into the simulator to enhance decision point management within the process model. These enhancements improve the performance of Rims in accurately simulating the real process in terms of control flow, as well as in terms of time and congestion dimensions. Especially in process scenarios with significant congestion – when a limited availability of resources leads to significant event queues for their allocation – the ability of Rims to use queue features to predict waiting times allows it to surpass the state-of-the-art. We evaluated our approach with real-world and synthetic event logs, using various metrics to assess the simulation model’s quality in terms of control-flow, time, and congestion dimensions.
  • Demo paper for tool accepted at BPM 2024
    We are happy to report our tool: Nirdizati Light: A Modular Framework for Explainable Predictive Process Monitoring, has been accepted at the Demo & Resources track for BPM 202 Authors: Andrei Buliga, Riccardo Graziosi, Chiara Di Francescomarino, Chiara Ghidini, Williams Rizzi, Massimiliano Ronzani, Fabrizio Maria Maggi Abstract: Nirdizati Light is an innovative Python package designed for Explainable Predictive Process Monitoring (XPPM). It addresses the need for a modular, flexible tool to compare predictive models, and generate explanations for the predictions made by the predictive models. By integrating consolidated frameworks libraries for process mining, machine learning, and explainable AI, it offers a comprehensive approach to predictive model construction and explanation generation. This paper discusses the tool’s key features, and its significance in the BPM community.
  • A paper on Generative AI in process mining at ICPM24
    The paper Generating the traces you need: a conditional generative model for Process Mining data by Riccardo Graziosi, Massimiliano Ronzani, Andrei Buliga, Chiara Di Francescomarino, Francesco Folino, Chiara Ghidini, Francesca Meneghello, and Luigi Pontieri has been accepted for presentation at ICPM 2024! Abstract: In recent years, trace generation has emerged as a significant challenge within the Process Mining community. Deep Learning (DL) models have demonstrated accuracy in reproducing the features of the selected processes. However, current DL generative models are limited in their ability to adapt the learned distributions to generate data samples based on specific conditions or attributes. This limitation is particularly significant because the ability to control the type of generated data can be beneficial in various contexts, enabling a focus on specific behaviours, exploration of infrequent patterns, or simulation of alternative ‘what-if’ scenarios. In this work, we address this challenge by introducing a conditional model for process data generation based on a conditional variational autoencoder (CVAE). Conditional models offer control over the generation process by tuning input conditional variables, enabling more targeted and controlled data generation. Unlike other domains, CVAE for process mining faces specific challenges due to the multiperspective nature of the data and the need to adhere to control-flow rules while ensuring data variability. Specifically, we focus on generating process executions conditioned on control flow and temporal features of the trace, allowing us to produce traces for specific, identified sub-processes. The generated traces are then evaluated using common metrics for generative model assessment, along with additional metrics to evaluate the quality of the conditional generation.
  • Two papers accepted at BPM 2024
    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.
  • Best Student Paper Award for Francesca Meneghello at ICPM 2023 (International Conference on Process Mining 2023)
    We are pleased to inform you of an important recognition obtained by our colleague Francesca Meneghello: The article “Runtime Integration of Machine Learning and Simulation for Business Processes” by Francesca Meneghello, Chiara Di Francescomarino and Chiara Ghidini won the Best Student Paper Award at ICPM2023 (International Conference on Process Mining 2023).
    The award is dedicated to the best conference paper where the first author is a student. Francesca Meneghello is a FBK PhD student who just finished her 1st year in the National Artificial Intelligence PhD convention.
  • Process Mining for Healthcare paper in Journal of Biomedical Informatics

    It’s out! Jorge Munoz-Gama, Niels Martinb, Carlos Fernandez-Llatas, Owen A. Johnson, Marcos Sepúlveda, Emmanuel Helm, Victor Galvez-Yanjari, Eric Rojas, Antonio Martinez-Millana, Davide Aloini, Ilaria Angela Amantea, Robert Andrews, Michael Arias, Iris Beerepoot, Elisabetta Benevento, Andrea Burattin, Daniel Capurro, Josep Carmona, Marco Comuzzi, Benjamin Dalmas, Rene de la Fuente, Chiara Di Francescomarino, Claudio Di Ciccio, Roberto Gatta, Chiara Ghidini, Fernanda Gonzalez-Lopez, Gema Ibanez-Sanchez, Hilda B.Klasky, Angelina Prima Kurniati, Xixi Lu, Felix Mannhardt, Ronny Mansa, Mar Marcos, Renata Medeiros de Carvalho, Marco Pegoraro, Simon K. Poon, Luise Pufahl, Hajo A.Reijers, Simon Remy, Stefanie Rinderle-Maa, Lucia Sacchi, Fernando Seoane, Minseok Song, Alessandro Stefanini, Emilio Sulis, Arthur H.M.ter Hofstede, Pieter J.Toussaint, Vicente Traver, Zoe Valero-Ramon, Inge van de Weerd, Wil M.P.van der Aalst, Rob Vanwersch, Mathias Weske, Moe Thandar Wynn, Francesca Zerbato. Process mining for healthcare: Characteristics and challenges, Journal of Biomedical Informatics, Volume 127, March 2022, 103994. https://doi.org/10.1016/j.jbi.2022.103994

    Abstract: Process mining techniques can be used to analyse business processes using the data logged during their execution. These techniques are leveraged in a wide range of domains, including healthcare, where it focuses mainly on the analysis of diagnostic, treatment, and organisational processes. Despite the huge amount of data generated in hospitals by staff and machinery involved in healthcare processes, there is no evidence of a systematic uptake of process mining beyond targeted case studies in a research context. When developing and using process mining in healthcare, distinguishing characteristics of healthcare processes such as their variability and patient-centred focus require targeted attention. Against this background, the Process-Oriented Data Science in Healthcare Alliance has been established to propagate the research and application of techniques targeting the data-driven improvement of healthcare processes. This paper, an initiative of the alliance, presents the distinguishing characteristics of the healthcare domain that need to be considered to successfully use process mining, as well as open challenges that need to be addressed by the community in the future.

     

  • We are part of the first Process MIning Summer School 2022

    We are part of the first Summer School on Process Mining organized by the IEEE Task Force on Process Mining will take place in Aachen, Germany from 4 to 8 July 2022 with a course on Predictive Process Monitoring!

  • Paper on Computational Persuasion at AAAI 2022

    The paper Machine Learning for Utility Prediction in Argument-Based Computational Persuasion by Ivan Donadello, Anthony Hunter, Stefano Teso, and Mauro Dragoni has been accepted for presentation at the main technical session at AAAI 2022!

    Abstract: Automated persuasion systems (APS) aim to persuade a user to believe something by entering into a dialogue in which arguments and counterarguments are exchanged. To maximize the probability that an APS is successful in persuading a user, it can identify a global policy that will allow it to select the best arguments it presents at each stage of the dialogue whatever arguments the user presents. However, in real applications, such as for healthcare, it is unlikely the utility of the outcome of the dialogue will be the same, or the exact opposite, for the APS and user. In order to deal with this situation, games in extended form have been harnessed for argumentation in Bi-party Decision Theory. This opens new problems that we address in this paper: (1) How can we use Machine Learning (ML) methods to predict utility functions for different subpopulations of users? and (2) How can we identify for a new user the best utility function from amongst those that we have learned? To this extent, we develop two ML methods, EAI and EDS, that leverage information coming from the users to predict their utilities. EAI is restricted to a fixed amount of information, whereas EDS can choose the information that best detects the subpopulations of a user. We evaluate EAI and EDS in a simulation setting and in a realistic case study concerning healthy eating habits. Results are promising in both cases, but EDS is more effective at predicting useful utility functions.

  • Paper on Reachability of Wf-nets in Expert Syst. Appl

    Its Out! Riccardo De Masellis, Chiara Di Francescomarino, Chiara Ghidini, Sergio Tessaris: Solving reachability problems on data-aware workflows. Expert Syst. Appl. 189: 116059 (2022). https://doi.org/10.1016/j.eswa.2021.116059

    Abstract: Recent advances in the field of Business Process Management (BPM) have brought about several suites able to model data objects along with the traditional control flow perspective. Nonetheless, when it comes to formal verification there is still a lack of effective verification tools on imperative data-aware process models and executions: the data perspective is often abstracted away and verification tools are often missing. Automated Planning is one of the core areas of Artificial Intelligence where theoretical investigations and concrete and robust tools have made possible the reasoning about dynamic systems and domains. Moreover planning techniques are gaining popularity in the context of BPM. Starting from these observations, we provide here a concrete framework for formal verification of reachability properties on an expressive, yet empirically tractable class of data-aware pro- cess models, an extension of Workflow Nets. Then we provide a rigorous map- ping between the semantics of such models and that of three important Auto- mated Planning paradigms: Action Languages, Classical Planning, and Model- Checking. Finally, we perform a comprehensive assessment of the performance of three popular tools supporting the above paradigms in solving reachability problems for imperative data-aware business processes, which paves the way for a theoretically well founded and practically viable exploitation of planning-based techniques on data-aware business processes.