A systematic review of synthetic event data generation: overview, challenges, and research directions. Kuhn, M., Zisgen, Y., Grüger, J., Maldonado, A., Koschmider, A., & Bergmann, R. Process Science, 3(1):26, 2026. ![A systematic review of synthetic event data generation: overview, challenges, and research directions [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Synthetic event data generation has emerged as a promising means of supporting process mining and Business Process Management (BPM) when real event logs are unavailable, sensitive, or unsuitable for controlled experimentation. Existing approaches range from traditional process-model simulation and rule-based generation to data-driven and hybrid methods. Synthetic event data can support benchmarking, data sharing, data augmentation, and what-if analysis, but its generation raises specific challenges, such as preserving temporal dependencies, addressing high uniqueness, and ensuring realistic and purposeful event logs. This study presents a systematic literature review of synthetic event data generation, based on an analysis of 52 papers, consolidating existing research to classify objectives, evaluate methods, and identify corresponding domains and challenges. By synthesizing findings from the literature, this study highlights key challenges, provides a comprehensive classification of methods, and outlines future research directions. The findings aim to guide researchers and practitioners in advancing the field of synthetic event data generation while addressing critical gaps in existing literature.
@article{Kuhn2026,
author = {Kuhn, Martin and Zisgen, Yorck and Grüger, Joscha and Maldonado, Andrea and Koschmider, Agnes and Bergmann, Ralph},
title = {A systematic review of synthetic event data generation: overview, challenges, and research directions},
journal = {Process Science},
year = {2026},
volume = {3},
number = {1},
pages = {26},
doi = {10.1007/s44311-026-00060-w},
url = {https://doi.org/10.1007/s44311-026-00060-w},
issn = {2948-2178},
abstract = {Synthetic event data generation has emerged as a promising means of supporting process mining and Business Process Management (BPM) when real event logs are unavailable, sensitive, or unsuitable for controlled experimentation. Existing approaches range from traditional process-model simulation and rule-based generation to data-driven and hybrid methods. Synthetic event data can support benchmarking, data sharing, data augmentation, and what-if analysis, but its generation raises specific challenges, such as preserving temporal dependencies, addressing high uniqueness, and ensuring realistic and purposeful event logs. This study presents a systematic literature review of synthetic event data generation, based on an analysis of 52 papers, consolidating existing research to classify objectives, evaluate methods, and identify corresponding domains and challenges. By synthesizing findings from the literature, this study highlights key challenges, provides a comprehensive classification of methods, and outlines future research directions. The findings aim to guide researchers and practitioners in advancing the field of synthetic event data generation while addressing critical gaps in existing literature.}
}
Downloads: 0
{"_id":"ekMKEdpwSqG2XL5kT","bibbaseid":"kuhn-zisgen-grger-maldonado-koschmider-bergmann-asystematicreviewofsyntheticeventdatagenerationoverviewchallengesandresearchdirections-2026","author_short":["Kuhn, M.","Zisgen, Y.","Grüger, J.","Maldonado, A.","Koschmider, A.","Bergmann, R."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Kuhn"],"firstnames":["Martin"],"suffixes":[]},{"propositions":[],"lastnames":["Zisgen"],"firstnames":["Yorck"],"suffixes":[]},{"propositions":[],"lastnames":["Grüger"],"firstnames":["Joscha"],"suffixes":[]},{"propositions":[],"lastnames":["Maldonado"],"firstnames":["Andrea"],"suffixes":[]},{"propositions":[],"lastnames":["Koschmider"],"firstnames":["Agnes"],"suffixes":[]},{"propositions":[],"lastnames":["Bergmann"],"firstnames":["Ralph"],"suffixes":[]}],"title":"A systematic review of synthetic event data generation: overview, challenges, and research directions","journal":"Process Science","year":"2026","volume":"3","number":"1","pages":"26","doi":"10.1007/s44311-026-00060-w","url":"https://doi.org/10.1007/s44311-026-00060-w","issn":"2948-2178","abstract":"Synthetic event data generation has emerged as a promising means of supporting process mining and Business Process Management (BPM) when real event logs are unavailable, sensitive, or unsuitable for controlled experimentation. Existing approaches range from traditional process-model simulation and rule-based generation to data-driven and hybrid methods. Synthetic event data can support benchmarking, data sharing, data augmentation, and what-if analysis, but its generation raises specific challenges, such as preserving temporal dependencies, addressing high uniqueness, and ensuring realistic and purposeful event logs. This study presents a systematic literature review of synthetic event data generation, based on an analysis of 52 papers, consolidating existing research to classify objectives, evaluate methods, and identify corresponding domains and challenges. By synthesizing findings from the literature, this study highlights key challenges, provides a comprehensive classification of methods, and outlines future research directions. The findings aim to guide researchers and practitioners in advancing the field of synthetic event data generation while addressing critical gaps in existing literature.","bibtex":"@article{Kuhn2026,\n author = {Kuhn, Martin and Zisgen, Yorck and Grüger, Joscha and Maldonado, Andrea and Koschmider, Agnes and Bergmann, Ralph},\n title = {A systematic review of synthetic event data generation: overview, challenges, and research directions},\n journal = {Process Science},\n year = {2026},\n volume = {3},\n number = {1},\n pages = {26},\n doi = {10.1007/s44311-026-00060-w},\n url = {https://doi.org/10.1007/s44311-026-00060-w},\n issn = {2948-2178},\n abstract = {Synthetic event data generation has emerged as a promising means of supporting process mining and Business Process Management (BPM) when real event logs are unavailable, sensitive, or unsuitable for controlled experimentation. Existing approaches range from traditional process-model simulation and rule-based generation to data-driven and hybrid methods. Synthetic event data can support benchmarking, data sharing, data augmentation, and what-if analysis, but its generation raises specific challenges, such as preserving temporal dependencies, addressing high uniqueness, and ensuring realistic and purposeful event logs. This study presents a systematic literature review of synthetic event data generation, based on an analysis of 52 papers, consolidating existing research to classify objectives, evaluate methods, and identify corresponding domains and challenges. By synthesizing findings from the literature, this study highlights key challenges, provides a comprehensive classification of methods, and outlines future research directions. The findings aim to guide researchers and practitioners in advancing the field of synthetic event data generation while addressing critical gaps in existing literature.}\n}\n\n\n","author_short":["Kuhn, M.","Zisgen, Y.","Grüger, J.","Maldonado, A.","Koschmider, A.","Bergmann, R."],"key":"Kuhn2026","id":"Kuhn2026","bibbaseid":"kuhn-zisgen-grger-maldonado-koschmider-bergmann-asystematicreviewofsyntheticeventdatagenerationoverviewchallengesandresearchdirections-2026","role":"author","urls":{"Paper":"https://doi.org/10.1007/s44311-026-00060-w"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"www.wi2.uni-trier.de/publications/WI2Publikationen.bib","dataSources":["MSp3DzP4ToPojqkFy","9v4v84gbRB6iyKeHb","FWPbCYSxS5WYzo747"],"keywords":[],"search_terms":["systematic","review","synthetic","event","data","generation","overview","challenges","research","directions","kuhn","zisgen","grüger","maldonado","koschmider","bergmann"],"title":"A systematic review of synthetic event data generation: overview, challenges, and research directions","year":2026}