The International Workshop on Leveraging Machine Learning in Process Mining - ML4PM - is a premier event that aims to foster collaboration and innovation in the intersection of machine learning and process mining. Over the past few years, the combination of these two fields has generated a lot of interest, and this workshop provides an excellent opportunity for researchers and practitioners to share their latest findings and explore new directions for future research.
The workshop will feature a diverse range of papers that showcase the latest advances in automated process modelling, predictive process mining, deep learning techniques, and online process mining. These themes reflect the most exciting and promising areas of research at the intersection of machine learning and process mining. By fostering dialogue and collaboration among participants, the workshop aims to catalyze breakthroughs and push the boundaries of what is possible in this exciting and rapidly-evolving field.
ML4PM 2024 will be held in Copenhagen, in conjunction with the ICPM conference.
This workshop invites papers that present works that lay in the intersection between machine learning and process mining. The event provides a suitable environment to discuss new approaches presented by researchers and practitioners. Main themes include automated process modeling, predictive process mining, application of deep learning techniques and online process mining. The workshop will count with leading researchers, engineers and scientists who are actively working on these topics.
Topics of interest for submission include, but are not limited to:
Contributions to all calls should be submitted electronically to the Workshop management system connecting to https://easychair.org/my/conference?conf=icpm2023. At least one author of each accepted paper is expected to participate in the conference and present his/her work.
Submissions must be original contributions that have not been published previously. Authors are requested to prepare submissions according to the format of the Lecture Notes in Business Information Processing (LNBIP) series by Springer href="http://www.springer.com/computer/lncs?SGWID=0-164-6-791344-0. Submissions must be in English and must not exceed 12 pages (including figures, bibliography and appendices). Each paper should contain a short abstract, clarifying the relation of the paper with the workshop topics, clearly state the problem being addressed, the goal of the work, the results achieved, and the relation to the literature.
A special issue of the Journal of Intelligent Information Systems (Springer, https://www.springer.com/journal/10844) devoted to a selection of the best ICPM workshop papers will be scheduled in the months following the conference.
Registrations are managed by the ICPM system
| Milestone | Deadline |
|---|---|
| Abstract Submission | August 08, 2024 |
| Paper Submission | August 15, 2024 |
| Notification of Acceptance | September 2, 2024 |
| Submission of Camera Ready Papers | September 23, 2024 |
| Workshop | October 14, 2024 |
| Post-workshop Camera-Ready Papers | October 29, 2024 |
Chiara Ghidini and Massimiliano Ronzani
Predictive Process Monitoring: the story so far and trends for the future.
Predictive Process Monitoring (PPM) is a relatively new branch of Process Mining that aims at predicting the future of an ongoing (uncompleted) process execution. Typical examples of predictions of the future of an execution trace relate to the outcome of a process execution, to its completion time, or to the sequence of its future activities. In establishing itself as one of the important research areas of Process Mining, PPM has also contributed, in a significant manner, to contaminate Process Mining with data driven Artificial Intelligence techniques, in particular stemming from Machine (Deep) Learning (ML). As ML evolves, often in a very energetic manner, so does PPM, partly driven by new ML techniques available and partly driven by specific challenges originating from the peculiarity of Process Mining data and requirements. In this talk we will provide an overview of what PPM has done so far and a personal reflection on new trends, future tasks, and challenges for this vibrant research area.
Sylvio Barbon Junior
TUTORIAL: Process Mining the Scikit-Learn Way: Introducing SkPM.
SkPM is an open-source extension of the popular Scikit-learn library, tailored specifically for Process Mining (PM) applications. It offers a standardized, reproducible, and user-friendly toolkit designed to bridge the gap between PM research and practical implementations. By integrating seamlessly with Scikit-learn, SkPM provides familiar workflows while enabling researchers and practitioners to apply machine learning techniques directly to process mining tasks, fostering a more efficient and accessible approach to analyzing and improving business processes. During this tutorial, attendees will be provided with a complete example of how to take advantage of this simplified library.
Help us to foster the discussion!
Please visit slido.com and type 3445 to share your views. Your input is invaluable in shaping the dialogue and focus of our workshop, and we appreciate your engagement!
| October 14th 2024 - Auditorium 83 - Building 116 DTU | ||
|---|---|---|
| Time | Title | Authors |
| Openig Session | ||
| 09:00 | Opening | Workshop Co-Chairs |
| 09:30 | Keynote Speech: Predictive Process Monitoring: the story so far and trends for the future. | Chiara Ghidini and Massimiliano Ronzani |
| 10:30 - 11:00 | COFFEE BREAK | |
| Session 1 | ||
| 11:00 | On the Impact of Low-Quality Activity Labels in Predictive Process Monitoring. | Marco Comuzzi, Sungkyu Kim, Jonghyeon Ko, Cinzia Cappiello, Musa Salamov and Barbara Pernici |
| 11:25 | Predictions in Predictive Process Monitoring with Previously Unseen Categorical Values. | Johannes Roider, Weixin Wang, Dario Zanca, Martin Matzner and Bjoern Eskofier |
| 11:45 | Mitigating Case-Length Distortion in Deep-Learning-Based Predictive Process Monitoring. | Brecht Wuyts, Seppe Vanden Broucke and Jochen De Weerdt |
| 12:10 | Differentially Private Event Logs with Case Attributes. | Hannes Ueck, Robert Andrews, Moe Thandar Wynn and Sander J.J. Leemans |
| 12:30 - 13:30 | LUNCH BREAK | |
| Session 2 | ||
| 13:30 | Enhancing Predictive Process Monitoring using semantic information. | Jiaxin Yuan, Daniela Grigori and Han van der Aa |
| 13:50 | Towards Accurate Predictions in ITSM: A Study on Transformer-Based Predictive Process Monitoring. | Marc C. Hennig |
| 14:15 | Process Model Forecasting: Univariate vs Multivariate Approaches. | Yongbo Yu, Jari Peeperkorn, Johannes De Smedt and Jochen De Weerdt |
| 14:35 | CC-HIT: Creating Counterfactuals from High-Impact Transitions | Zhicong Xian, Ludwig Zellner, Gabriel Marques Tavares and Thomas Seidl |
| 15:00 - 15:30 | COFFEE BREAK | |
| Session 3 | ||
| 15:30 | Tutorial:Process Mining the Scikit-Learn Way: Introducing SkPM. | Sylvio Barbon Junior |
| 17:15 | Buses departing for WELCOME RECEPTION | |
