Supervised conformance checking using recurrent neural network classifiers
- Author
- Jari Peeperkorn, Seppe vanden Broucke (UGent) and Jochen De Weerdt
- Organization
- Abstract
- Conformance checking is concerned with the task of assessing the quality of process models describing actual behavior captured in an event log across different dimensions. In this paper, a novel approach for obtaining the degree of recall and precision between a process model and event log is introduced. The approach relies on the generation of a so-called “antilog”, randomly constructed from the activity vocabulary, on one hand, and a simulated “model log”, which is played-out from the given model. In the case of recall the antilog and model log are used to train a recurrent neural network classifier. This network allows for calculating the probability of a trace being part of the model log or the antilog. If thereupon the event log is fed to the neural network, a value for recall can be obtained. In the case of precision the neural network is trained using a given event log and the antilog, and the model log is fed to it afterwards. We show that this new method can be used to measure global recall and precision correctly in some common examples.
Downloads
-
110.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 610.15 KB
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 706.50 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8751961
- MLA
- Peeperkorn, Jari, et al. “Supervised Conformance Checking Using Recurrent Neural Network Classifiers.” Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers, edited by Sander Leemans and Henrik Leopold, vol. 406, Springer, 2021, pp. 175–87, doi:10.1007/978-3-030-72693-5_14.
- APA
- Peeperkorn, J., vanden Broucke, S., & De Weerdt, J. (2021). Supervised conformance checking using recurrent neural network classifiers. In S. Leemans & H. Leopold (Eds.), Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers (Vol. 406, pp. 175–187). https://doi.org/10.1007/978-3-030-72693-5_14
- Chicago author-date
- Peeperkorn, Jari, Seppe vanden Broucke, and Jochen De Weerdt. 2021. “Supervised Conformance Checking Using Recurrent Neural Network Classifiers.” In Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers, edited by Sander Leemans and Henrik Leopold, 406:175–87. Springer. https://doi.org/10.1007/978-3-030-72693-5_14.
- Chicago author-date (all authors)
- Peeperkorn, Jari, Seppe vanden Broucke, and Jochen De Weerdt. 2021. “Supervised Conformance Checking Using Recurrent Neural Network Classifiers.” In Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers, ed by. Sander Leemans and Henrik Leopold, 406:175–187. Springer. doi:10.1007/978-3-030-72693-5_14.
- Vancouver
- 1.Peeperkorn J, vanden Broucke S, De Weerdt J. Supervised conformance checking using recurrent neural network classifiers. In: Leemans S, Leopold H, editors. Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers. Springer; 2021. p. 175–87.
- IEEE
- [1]J. Peeperkorn, S. vanden Broucke, and J. De Weerdt, “Supervised conformance checking using recurrent neural network classifiers,” in Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers, Padua, Italy, 2021, vol. 406, pp. 175–187.
@inproceedings{8751961,
abstract = {{Conformance checking is concerned with the task of assessing the quality of process models describing actual behavior captured in an event log across different dimensions. In this paper, a novel approach for obtaining the degree of recall and precision between a process model and event log is introduced. The approach relies on the generation of a so-called “antilog”, randomly constructed from the activity vocabulary, on one hand, and a simulated “model log”, which is played-out from the given model. In the case of recall the antilog and model log are used to train a recurrent neural network classifier. This network allows for calculating the probability of a trace being part of the model log or the antilog. If thereupon the event log is fed to the neural network, a value for recall can be obtained. In the case of precision the neural network is trained using a given event log and the antilog, and the model log is fed to it afterwards. We show that this new method can be used to measure global recall and precision correctly in some common examples.}},
author = {{Peeperkorn, Jari and vanden Broucke, Seppe and De Weerdt, Jochen}},
booktitle = {{Process Mining Workshops, ICPM 2020 International Workshops, Revised Selected Papers}},
editor = {{Leemans, Sander and Leopold, Henrik}},
isbn = {{9783030726928}},
issn = {{1865-1348}},
language = {{eng}},
location = {{Padua, Italy}},
pages = {{175--187}},
publisher = {{Springer}},
title = {{Supervised conformance checking using recurrent neural network classifiers}},
url = {{http://doi.org/10.1007/978-3-030-72693-5_14}},
volume = {{406}},
year = {{2021}},
}
- Altmetric
- View in Altmetric