Conformance checking using activity and trace embeddings
- Author
- Jari Peeperkorn, Seppe vanden Broucke (UGent) and Jochen De Weerdt
- Organization
- Abstract
- Conformance checking describes process mining techniques used to compare an event log and a corresponding process model. In this paper, we propose an entirely new approach to conformance checking based on neural network-based embeddings. These embeddings are vector representations of every activity/task present in the model and log, obtained via act2vec, a Word2vec based model. Our novel conformance checking approach applies the Word Mover’s Distance to the activity embeddings of traces in order to measure fitness and precision. In addition, we investigate a more efficiently calculated lower bound of the former metric, i.e. the Iterative Constrained Transfers measure. An alternative method using trace2vec, a Doc2vec based model, to train and compare vector representations of the process instances themselves is also introduced. These methods are tested in different settings and compared to other conformance checking techniques, showing promising results.
Downloads
-
BPM2020 3 .pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 654.40 KB
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 851.81 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8688065
- MLA
- Peeperkorn, Jari, et al. “Conformance Checking Using Activity and Trace Embeddings.” Business Process Management Forum, Proceedings, edited by Dirk Fahland et al., vol. 392, Springer, 2020, pp. 105–21, doi:10.1007/978-3-030-58638-6_7.
- APA
- Peeperkorn, J., vanden Broucke, S., & De Weerdt, J. (2020). Conformance checking using activity and trace embeddings. In D. Fahland, C. Ghidini, J. Becker, & M. Dumas (Eds.), Business process management forum, Proceedings (Vol. 392, pp. 105–121). https://doi.org/10.1007/978-3-030-58638-6_7
- Chicago author-date
- Peeperkorn, Jari, Seppe vanden Broucke, and Jochen De Weerdt. 2020. “Conformance Checking Using Activity and Trace Embeddings.” In Business Process Management Forum, Proceedings, edited by Dirk Fahland, Chiara Ghidini, Jörg Becker, and Marlon Dumas, 392:105–21. Springer. https://doi.org/10.1007/978-3-030-58638-6_7.
- Chicago author-date (all authors)
- Peeperkorn, Jari, Seppe vanden Broucke, and Jochen De Weerdt. 2020. “Conformance Checking Using Activity and Trace Embeddings.” In Business Process Management Forum, Proceedings, ed by. Dirk Fahland, Chiara Ghidini, Jörg Becker, and Marlon Dumas, 392:105–121. Springer. doi:10.1007/978-3-030-58638-6_7.
- Vancouver
- 1.Peeperkorn J, vanden Broucke S, De Weerdt J. Conformance checking using activity and trace embeddings. In: Fahland D, Ghidini C, Becker J, Dumas M, editors. Business process management forum, Proceedings. Springer; 2020. p. 105–21.
- IEEE
- [1]J. Peeperkorn, S. vanden Broucke, and J. De Weerdt, “Conformance checking using activity and trace embeddings,” in Business process management forum, Proceedings, Seville, Spain, 2020, vol. 392, pp. 105–121.
@inproceedings{8688065,
abstract = {{Conformance checking describes process mining techniques used to compare an event log and a corresponding process model. In this paper, we propose an entirely new approach to conformance checking based on neural network-based embeddings. These embeddings are vector representations of every activity/task present in the model and log, obtained via act2vec, a Word2vec based model. Our novel conformance checking approach applies the Word Mover’s Distance to the activity embeddings of traces in order to measure fitness and precision. In addition, we investigate a more efficiently calculated lower bound of the former metric, i.e. the Iterative Constrained Transfers measure. An alternative method using trace2vec, a Doc2vec based model, to train and compare vector representations of the process instances themselves is also introduced. These methods are tested in different settings and compared to other conformance checking techniques, showing promising results.}},
author = {{Peeperkorn, Jari and vanden Broucke, Seppe and De Weerdt, Jochen}},
booktitle = {{Business process management forum, Proceedings}},
editor = {{Fahland, Dirk and Ghidini, Chiara and Becker, Jörg and Dumas, Marlon}},
isbn = {{9783030586379}},
issn = {{1865-1348}},
language = {{eng}},
location = {{Seville, Spain}},
pages = {{105--121}},
publisher = {{Springer}},
title = {{Conformance checking using activity and trace embeddings}},
url = {{http://doi.org/10.1007/978-3-030-58638-6_7}},
volume = {{392}},
year = {{2020}},
}
- Altmetric
- View in Altmetric