Luka Abb
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luka Abb has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jana-Rebecca Rehse
University of Mannheim
10 shared publications - Timotheus Kampik
Umeå University
3 shared publications - Majid Rafiei
RWTH Aachen University
2 shared publications - Michael Grohs
University of Mannheim
2 shared publications - Nourhan Elsayed
University of Mannheim
2 shared publications - Peter Fettke
Saarland University
2 shared publications
Latest Publications
- 14 June 2025
- Published by Springer Nature
- p. 19-35
Identifying Process Improvement Opportunities Through Process Execution Benchmarking
- 14 June 2025
- Published by Springer Nature
- p. 19-35
Identifying Process Improvement Opportunities Through Process Execution Benchmarking
- Open Access
Identifying Process Improvement Opportunities through Process Execution Benchmarking
Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do not suggest any measures to close potential performance gaps. To address this limitation, we propose a prescriptive technique for process execution benchmarking that recommends targeted process changes to improve process performance. The technique compares an event log from an ``own'' process to one from a selected benchmark process to identify potential activity replacements, based on behavioral similarity. It then evaluates each proposed change in terms of its feasibility and its estimated performance impact. The result is a list of potential process modifications that can serve as evidence-based decision support for process improvement initiatives.
Open AccessIdentifying Process Improvement Opportunities through Process Execution Benchmarking
Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do not suggest any measures to close potential performance gaps. To address this limitation, we propose a prescriptive technique for process execution benchmarking that recommends targeted process changes to improve process performance. The technique compares an event log from an ``own'' process to one from a selected benchmark process to identify potential activity replacements, based on behavioral similarity. It then evaluates each proposed change in terms of its feasibility and its estimated performance impact. The result is a list of potential process modifications that can serve as evidence-based decision support for process improvement initiatives.
- 30 August 2024
- Published by Springer Nature
- p. 20-36
Multivariate Anomaly Detection in Object-Centric Event Data
- 30 August 2024
- Published by Springer Nature
- p. 20-36
Multivariate Anomaly Detection in Object-Centric Event Data
- Open Access
- 13 April 2024
- Published by Elsevier in Information Systems
- Vol. 124
Process-related user interaction logs: State of the art, reference model, and object-centric implementation
- 13 April 2024
- Published by Elsevier in Information Systems
- Vol. 124
Open AccessProcess-related user interaction logs: State of the art, reference model, and object-centric implementation
- 11 January 2024
- Published by Springer Nature
- p. 18-30
A Discussion on Generalization in Next-Activity Prediction
- 11 January 2024
- Published by Springer Nature
- p. 18-30
A Discussion on Generalization in Next-Activity Prediction
- Top Cited Papers
- 11 January 2024
- Published by Springer Nature
- p. 453-465
Large Language Models Can Accomplish Business Process Management Tasks
- 11 January 2024
- Published by Springer Nature
- p. 453-465
Top Cited PapersLarge Language Models Can Accomplish Business Process Management Tasks
- Open Access
- 5 January 2024
- Published by Springer Nature in Business & Information Systems Engineering
- Vol. 66 (6) , 799-816
User Behavior Mining
Studying the behavior of users in software systems has become an essential task for software vendors who want to mitigate usability problems and identify automation potentials, or for researchers who want to test behavioral theories. One approach to studying user behavior in a data-driven way is through the analysis of so-called user interaction (UI) logs, which record the low-level activities that a user performs while executing a task. In the paper, the authors refer to the analysis of UI logs as User Behavior Mining (UBM) and position it as a research topic. UBM is conceptualized by means of a four-component framework that elaborates how UBM data can be captured, which technologies can be applied to analyze it, which objectives UBM can accomplish, and how theories can guide the analytical process. The applicability of the framework is demonstrated by three exemplary applications from an ongoing research project with a partner company. Finally, the paper discusses practical challenges to UBM and derives an agenda for potential future research directions.
- 5 January 2024
- Published by Springer Nature in Business & Information Systems Engineering
- Vol. 66 (6) , 799-816
Open AccessUser Behavior Mining
Studying the behavior of users in software systems has become an essential task for software vendors who want to mitigate usability problems and identify automation potentials, or for researchers who want to test behavioral theories. One approach to studying user behavior in a data-driven way is through the analysis of so-called user interaction (UI) logs, which record the low-level activities that a user performs while executing a task. In the paper, the authors refer to the analysis of UI logs as User Behavior Mining (UBM) and position it as a research topic. UBM is conceptualized by means of a four-component framework that elaborates how UBM data can be captured, which technologies can be applied to analyze it, which objectives UBM can accomplish, and how theories can guide the analytical process. The applicability of the framework is demonstrated by three exemplary applications from an ongoing research project with a partner company. Finally, the paper discusses practical challenges to UBM and derives an agenda for potential future research directions.
- Open Access
A Discussion on Generalization in Next-Activity Prediction
Next activity prediction aims to forecast the future behavior of running process instances. Recent publications in this field predominantly employ deep learning techniques and evaluate their prediction performance using publicly available event logs. This paper presents empirical evidence that calls into question the effectiveness of these current evaluation approaches. We show that there is an enormous amount of example leakage in all of the commonly used event logs, so that rather trivial prediction approaches perform almost as well as ones that leverage deep learning. We further argue that designing robust evaluations requires a more profound conceptual engagement with the topic of next-activity prediction, and specifically with the notion of generalization to new data. To this end, we present various prediction scenarios that necessitate different types of generalization to guide future research.
Open AccessA Discussion on Generalization in Next-Activity Prediction
Next activity prediction aims to forecast the future behavior of running process instances. Recent publications in this field predominantly employ deep learning techniques and evaluate their prediction performance using publicly available event logs. This paper presents empirical evidence that calls into question the effectiveness of these current evaluation approaches. We show that there is an enormous amount of example leakage in all of the commonly used event logs, so that rather trivial prediction approaches perform almost as well as ones that leverage deep learning. We further argue that designing robust evaluations requires a more profound conceptual engagement with the topic of next-activity prediction, and specifically with the notion of generalization to new data. To this end, we present various prediction scenarios that necessitate different types of generalization to guide future research.
- Open Access
Large Language Models can accomplish Business Process Management Tasks
Business Process Management (BPM) aims to improve organizational activities and their outcomes by managing the underlying processes. To achieve this, it is often necessary to consider information from various sources, including unstructured textual documents. Therefore, researchers have developed several BPM-specific solutions that extract information from textual documents using Natural Language Processing techniques. These solutions are specific to their respective tasks and cannot accomplish multiple process-related problems as a general-purpose instrument. However, in light of the recent emergence of Large Language Models (LLMs) with remarkable reasoning capabilities, such a general-purpose instrument with multiple applications now appears attainable. In this paper, we illustrate how LLMs can accomplish text-related BPM tasks by applying a specific LLM to three exemplary tasks: mining imperative process models from textual descriptions, mining declarative process models from textual descriptions, and assessing the suitability of process tasks from textual descriptions for robotic process automation. We show that, without extensive configuration or prompt engineering, LLMs perform comparably to or better than existing solutions and discuss implications for future BPM research as well as practical usage.
Open AccessLarge Language Models can accomplish Business Process Management Tasks
Business Process Management (BPM) aims to improve organizational activities and their outcomes by managing the underlying processes. To achieve this, it is often necessary to consider information from various sources, including unstructured textual documents. Therefore, researchers have developed several BPM-specific solutions that extract information from textual documents using Natural Language Processing techniques. These solutions are specific to their respective tasks and cannot accomplish multiple process-related problems as a general-purpose instrument. However, in light of the recent emergence of Large Language Models (LLMs) with remarkable reasoning capabilities, such a general-purpose instrument with multiple applications now appears attainable. In this paper, we illustrate how LLMs can accomplish text-related BPM tasks by applying a specific LLM to three exemplary tasks: mining imperative process models from textual descriptions, mining declarative process models from textual descriptions, and assessing the suitability of process tasks from textual descriptions for robotic process automation. We show that, without extensive configuration or prompt engineering, LLMs perform comparably to or better than existing solutions and discuss implications for future BPM research as well as practical usage.
- 7 September 2022
- Published by Springer Nature
- p. 57-74
A Reference Data Model for Process-Related User Interaction Logs
- 7 September 2022
- Published by Springer Nature
- p. 57-74
A Reference Data Model for Process-Related User Interaction Logs