A genetic algorithm for discovering process trees

J.C.A.M. Buijs; B.F. Dongen, van; W.M.P. Aalst, van der

doi:10.1109/CEC.2012.6256458

A genetic algorithm for discovering process trees

J.C.A.M. Buijs, B.F. Dongen, van, W.M.P. Aalst, van der

Process Analytics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

125 Citations (Scopus)

8 Downloads (Pure)

Abstract

Existing process discovery approaches have problems dealing with competing quality dimensions (fitness, simplicity, generalization, and precision) and may produce anomalous process models (e.g., deadlocking models). In this paper we propose a new genetic process mining algorithm that discovers process models from event logs. The tree representation ensures the soundness of the model. Moreover, as experiments show, it is possible to balance the different quality dimensions. Our genetic process mining algorithm is the first algorithm where the search process can be guided by preferences of the user while ensuring correctness.

Original language	English
Title of host publication	Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2012, Brisbane, Australia, June 10-15, 2012)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1-8
ISBN (Print)	978-1-4673-1510-4
DOIs	https://doi.org/10.1109/CEC.2012.6256458
Publication status	Published - 2012
Event	conference; IEEE Congress on Evolutionary Computation; 2012-06-10; 2012-06-15 - Duration: 10 Jun 2012 → 15 Jun 2012

Conference

Conference	conference; IEEE Congress on Evolutionary Computation; 2012-06-10; 2012-06-15
Period	10/06/12 → 15/06/12
Other	IEEE Congress on Evolutionary Computation

Access to Document

10.1109/CEC.2012.6256458

Cite this

@inproceedings{a3f8292083b04cac861bf589977677fc,

title = "A genetic algorithm for discovering process trees",

abstract = "Existing process discovery approaches have problems dealing with competing quality dimensions (fitness, simplicity, generalization, and precision) and may produce anomalous process models (e.g., deadlocking models). In this paper we propose a new genetic process mining algorithm that discovers process models from event logs. The tree representation ensures the soundness of the model. Moreover, as experiments show, it is possible to balance the different quality dimensions. Our genetic process mining algorithm is the first algorithm where the search process can be guided by preferences of the user while ensuring correctness.",

author = "J.C.A.M. Buijs and \{Dongen, van\}, B.F. and \{Aalst, van der\}, W.M.P.",

year = "2012",

doi = "10.1109/CEC.2012.6256458",

language = "English",

isbn = "978-1-4673-1510-4",

pages = "1--8",

booktitle = "Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2012, Brisbane, Australia, June 10-15, 2012)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "conference; IEEE Congress on Evolutionary Computation; 2012-06-10; 2012-06-15 ; Conference date: 10-06-2012 Through 15-06-2012",

}

Buijs, JCAM, Dongen, van, BF & Aalst, van der, WMP 2012, A genetic algorithm for discovering process trees. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2012, Brisbane, Australia, June 10-15, 2012). Institute of Electrical and Electronics Engineers, Piscataway, pp. 1-8, conference; IEEE Congress on Evolutionary Computation; 2012-06-10; 2012-06-15, 10/06/12. https://doi.org/10.1109/CEC.2012.6256458

A genetic algorithm for discovering process trees. / Buijs, J.C.A.M.; Dongen, van, B.F.; Aalst, van der, W.M.P.
Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2012, Brisbane, Australia, June 10-15, 2012). Piscataway: Institute of Electrical and Electronics Engineers, 2012. p. 1-8.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A genetic algorithm for discovering process trees

AU - Buijs, J.C.A.M.

AU - Dongen, van, B.F.

AU - Aalst, van der, W.M.P.

PY - 2012

Y1 - 2012

N2 - Existing process discovery approaches have problems dealing with competing quality dimensions (fitness, simplicity, generalization, and precision) and may produce anomalous process models (e.g., deadlocking models). In this paper we propose a new genetic process mining algorithm that discovers process models from event logs. The tree representation ensures the soundness of the model. Moreover, as experiments show, it is possible to balance the different quality dimensions. Our genetic process mining algorithm is the first algorithm where the search process can be guided by preferences of the user while ensuring correctness.

AB - Existing process discovery approaches have problems dealing with competing quality dimensions (fitness, simplicity, generalization, and precision) and may produce anomalous process models (e.g., deadlocking models). In this paper we propose a new genetic process mining algorithm that discovers process models from event logs. The tree representation ensures the soundness of the model. Moreover, as experiments show, it is possible to balance the different quality dimensions. Our genetic process mining algorithm is the first algorithm where the search process can be guided by preferences of the user while ensuring correctness.

U2 - 10.1109/CEC.2012.6256458

DO - 10.1109/CEC.2012.6256458

M3 - Conference contribution

SN - 978-1-4673-1510-4

SP - 1

EP - 8

BT - Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2012, Brisbane, Australia, June 10-15, 2012)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - conference; IEEE Congress on Evolutionary Computation; 2012-06-10; 2012-06-15

Y2 - 10 June 2012 through 15 June 2012

ER -

A genetic algorithm for discovering process trees

Abstract

Conference

Access to Document

Fingerprint

Cite this