Wolfgang Kratsch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wolfgang Kratsch has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Maximilian Röglinger
FIM Research Center, University of Bayreuth, Bayreuth, Germany
9 shared publications - Andreas Egger
FIM Research Center for Information Management, Branch Business & Information Systems Engineering of the Fraunhofer FIT, Augsburg, Germany
5 shared publications - Christoph Kecht
FIM Research Center for Information Management, Augsburg, Germany
4 shared publications - Moe Thandar Wynn
Queensland University of Technology
4 shared publications - Alina Buss
Technical University of Munich
3 shared publications - Fabian König
FIM Research Center for Information Management, Branch Business & Information Systems Engineering of the Fraunhofer FIT, Augsburg, Germany and Augsburg Technical University of Applied Sciences, Augsburg, Germany
3 shared publications
Latest Publications
- Open Access
- 6 March 2026
- Published by Elsevier in Information Systems
- Vol. 140
Process mining between the lines: Extracting object-centric event logs from textual data
- 6 March 2026
- Published by Elsevier in Information Systems
- Vol. 140
Open AccessProcess mining between the lines: Extracting object-centric event logs from textual data
- Open Access
- 4 March 2026
- Published by Elsevier in Information Systems
- Vol. 140
Domain experts in the loop: Leveraging generative artificial intelligence for interactive data validation in process mining
- 4 March 2026
- Published by Elsevier in Information Systems
- Vol. 140
Open AccessDomain experts in the loop: Leveraging generative artificial intelligence for interactive data validation in process mining
- Open Access
- 8 January 2026
- Published by Springer Nature in Process Science
- Vol. 3 (1) , 1
Process Improvement Copilot: bridging the gap between process inefficiencies and process improvement ideas
Business process improvement (BPI) is a crucial value-adding stage of business process management, as it introduces process changes to eliminate flaws and enhance performance. However, the inherent demands of BPI on domain knowledge, process expertise, time, and creativity in conjunction with a scarcity of adequate computational support, hinder organizations from fully leveraging BPI. Recognizing this gap, recent research calls for all types of contributions to process improvement and innovation systems (PIISs), from design knowledge to software artifacts. Leveraging the latest developments in generative artificial intelligence, increased availability of process execution data, and extensive collections of BPI knowledge, we propose a new technical approach to supporting the generation of process improvement ideas in BPI initiatives. To this end, we develop the Process Improvement Copilot – a retrieval-augmented generation (RAG)-enhanced PIIS that generates context-specific process improvement ideas and provides related justification, thereby facilitating their further evaluation and implementation. This research contributes a novel technical approach to automated BPI by exploring a RAG-based use case, designing a corresponding system architecture, developing a software prototype to demonstrate its technical feasibility, and evaluating the Process Improvement Copilot’s usefulness in a naturalistic workshop setting.
- 8 January 2026
- Published by Springer Nature in Process Science
- Vol. 3 (1) , 1
Open AccessProcess Improvement Copilot: bridging the gap between process inefficiencies and process improvement ideas
Business process improvement (BPI) is a crucial value-adding stage of business process management, as it introduces process changes to eliminate flaws and enhance performance. However, the inherent demands of BPI on domain knowledge, process expertise, time, and creativity in conjunction with a scarcity of adequate computational support, hinder organizations from fully leveraging BPI. Recognizing this gap, recent research calls for all types of contributions to process improvement and innovation systems (PIISs), from design knowledge to software artifacts. Leveraging the latest developments in generative artificial intelligence, increased availability of process execution data, and extensive collections of BPI knowledge, we propose a new technical approach to supporting the generation of process improvement ideas in BPI initiatives. To this end, we develop the Process Improvement Copilot – a retrieval-augmented generation (RAG)-enhanced PIIS that generates context-specific process improvement ideas and provides related justification, thereby facilitating their further evaluation and implementation. This research contributes a novel technical approach to automated BPI by exploring a RAG-based use case, designing a corresponding system architecture, developing a software prototype to demonstrate its technical feasibility, and evaluating the Process Improvement Copilot’s usefulness in a naturalistic workshop setting.
- Open Access
- 4 November 2025
- Published by Elsevier in Decision Support Systems
- Vol. 200
Leveraging large language models for enhanced process model comprehension
- 4 November 2025
- Published by Elsevier in Decision Support Systems
- Vol. 200
Open AccessLeveraging large language models for enhanced process model comprehension
- Open Access
- 3 October 2025
- Published by Elsevier in Decision Support Systems
- Vol. 199
Beyond assumptions: A reference architecture to enable unsupervised process discovery from video data
- 3 October 2025
- Published by Elsevier in Decision Support Systems
- Vol. 199
Open AccessBeyond assumptions: A reference architecture to enable unsupervised process discovery from video data
- 7 June 2025
- Published by Springer Nature
- p. 37-44
From Words to Workflows: Extracting Object-Centric Event Logs from Textual Data
- 7 June 2025
- Published by Springer Nature
- p. 37-44
From Words to Workflows: Extracting Object-Centric Event Logs from Textual Data
- Open Access
- 15 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Management Information Systems
- Vol. 16 (3) , 1-34
Unstructured Data in Process Mining: A Systematic Literature Review
A large proportion of available data is in unstructured form such as text, image, and video data. As data analysis methods continue to improve, it becomes easier to tap into and exploit unstructured data. Even in the process mining discipline, which is traditionally focused on structured data stored in process-aware information systems, solutions that integrate unstructured data receive increasing attention. To date, however, there is no empirical overview on how unstructured data is leveraged in process mining. This lack of insight also makes it difficult to identify the most promising avenues to advance process mining research. To address this issue, the study presents a systematic literature review, analyzing 24 primary studies selected from a total of 1,379 search results (i.e., research items) at the intersection of unstructured data and process mining. One of the main findings is that current research predominantly deals with textual data and concentrates on extracting event logs for process discovery. To guide future process mining research, the study proposes a research agenda that includes seven opportunities to address the identified research gaps.
- 15 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Management Information Systems
- Vol. 16 (3) , 1-34
Open AccessUnstructured Data in Process Mining: A Systematic Literature Review
A large proportion of available data is in unstructured form such as text, image, and video data. As data analysis methods continue to improve, it becomes easier to tap into and exploit unstructured data. Even in the process mining discipline, which is traditionally focused on structured data stored in process-aware information systems, solutions that integrate unstructured data receive increasing attention. To date, however, there is no empirical overview on how unstructured data is leveraged in process mining. This lack of insight also makes it difficult to identify the most promising avenues to advance process mining research. To address this issue, the study presents a systematic literature review, analyzing 24 primary studies selected from a total of 1,379 search results (i.e., research items) at the intersection of unstructured data and process mining. One of the main findings is that current research predominantly deals with textual data and concentrates on extracting event logs for process discovery. To guide future process mining research, the study proposes a research agenda that includes seven opportunities to address the identified research gaps.
- 20 February 2025
- Published by Springer Nature
- p. 221-232
ProcessLLM: A Large Language Model Specialized in the Interpretation, Analysis, and Optimization of Business Processes
- 20 February 2025
- Published by Springer Nature
- p. 221-232
ProcessLLM: A Large Language Model Specialized in the Interpretation, Analysis, and Optimization of Business Processes
- Open Access
- 8 July 2024
- Published by Elsevier in Data in Brief
- Vol. 55, 110716
A multimedia dataset for object-centric business process mining in IT asset management
- 8 July 2024
- Published by Elsevier in Data in Brief
- Vol. 55, 110716
Open AccessA multimedia dataset for object-centric business process mining in IT asset management
- 1 September 2023
- Published by Springer Nature
- p. 196-213
Analytics Pipeline for Process Mining on Video Data
- 1 September 2023
- Published by Springer Nature
- p. 196-213
Analytics Pipeline for Process Mining on Video Data