Summer School Program Details

Thursday, August 27 Day 1

Time	Program
POSCO International Center Large-size Meeting Room (1F)
08:45 ~ 09:00	Opening Minseok Song (POSTECH, South Korea), Marco Comuzzi (UNIST, South Korea)
09:00 ~ 10:30	Unlocking Process Intelligence: A 360 Degree Introduction to Process Mining Wil van der Aalst (RWTH Aachen University, Germany) Process mining serves as the essential bridge between data science and process science, utilizing event data to reveal how operational processes actually function in the real world. This session explores the core pillars of the field — discovery, conformance, and performance — demonstrating how organizations can automatically transform “digital footprints” into actionable insights and process improvements. By examining diverse process modeling notations such as BPMN and Petri nets alongside event data standards such as XES and OCEL, you will learn to navigate end-to-end processes, eliminate bottlenecks, and ensure compliance.
10:45 ~ 12:15	From Event Logs to Process Logic: The Basics of Process Discovery Wil van der Aalst (RWTH Aachen University, Germany) Process discovery automatically constructs models from event data, yet it must navigate the complex trade-offs between recall, precision, generalization, and simplicity. This session introduces the Directly-Follows Graph (DFG) as a scalable baseline and demonstrates how advanced filtering techniques are essential for isolating dominant behavior from infrequent “noise”. We will dive into the core foundations of both bottom-up discovery — uncovering local patterns through the Alpha algorithm — and top-down discovery, which uses inductive mining to recursively decompose logs into sound-by-construction process trees.
12:15 ~ 13:30	Lunch
13:30 ~ 14:30	Conformance Checking: Token-Based Replay and Alignments Wil van der Aalst (RWTH Aachen University, Germany) The goal of conformance checking is to compare observed behavior (i.e., event data) with modeled behavior (e.g., a BPMN model, a Petri net, or DFG) to discover compliance problems and diagnose them. This session explains the key techniques for conformance checking: token-based replay and alignments. These techniques are also needed to project performance information onto process models, enable machine learning on process data, and to evaluate process discovery techniques.
14:45 ~ 15:30	Building Strong Data Foundations for Process Mining Moe Wynn (Queensland University of Technology, Australia) Process event data is the cornerstone of process mining. The quality and structure of this data directly determine the accuracy and value of process mining insights. Thus, building high-quality event logs is essential for generating trustworthy insights and driving meaningful process improvements. This session will cover the core structures of case-centric and object-centric event data, discuss key considerations for event log preparation, and demonstrate the impact of data quality on process mining results.
15:45 ~ 16:45	Process Mining Hands-On A Poornima Dhall (Celonis)
17:00 ~ 18:00	Process Mining Hands-On B: AI Agent Mining in Practice Julian Lebherz, Tony (RaeSung) Park (SAP BTM)
18:00 ~	Dinner & Networking

Friday, August 28 Day 2

Time	Program
POSCO International Center Large-size Meeting Room (1F)
08:45 ~ 09:45	Unleashing Predictive and Generative AI in Process Mining Marco Comuzzi (UNIST, South Korea) This lecture examines the evolution of artificial intelligence (AI) in process mining over the past decade. It begins by exploring how predictive models of key process aspects can be developed by applying traditional machine learning techniques to event log data. The session then turns to the emerging role of generative AI, with a particular focus on Large Language Models (LLMs), and their potential to transform process mining. After analyzing how LLMs can influence different stages of the process mining lifecycle, the lecture concludes with a concrete application that leverages LLMs to assess and enhance the quality of event log data.
10:00 ~ 10:45	Federated Process Mining: Federated Event Log Generation for Process Discovery across Organizational Boundaries Bernardo Nugroho Yahya (Hankuk University of Foreign Studies, South Korea) This lecture introduces Federated Process Mining, a method for anonymizing local event logs and merging them into a federated event log. In the supply chain processes where multiple organizations are involved, it poses crucial challenges due to the information silo, privacy and interoperability concerns. The session introduces the concept of Horizontal Federated Learning (same process, different cohorts) and Vertical Federated Learning (same case split across organizational stages). The session details how local log anonymization, privacy-preserving event correlation, and federated log construction enable end-to-end process discovery across organizational boundaries without exposing transactional data.
10:45 ~ 11:30	Process Mining Case Studies Angelina Prima Kurniati (Telkom University, Indonesia)
11:30 ~ 12:15	Evidence-Based Evaluation of Process Mining in Healthcare Simon Poon (The University of Sydney, Australia)
12:15 ~ 12:30	Closing Minseok Song (POSTECH, South Korea), Marco Comuzzi (UNIST, South Korea)
12:30 ~	Lunch