All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees

Jan Martijn E.M. van der Werf; Artem Polyvyanyy; Bart R. van Wensveen; Matthieu J. S. Brinkhuis; Hajo A. Reijers

doi:10.1007/978-3-030-79382-1_9

All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees

Jan Martijn E.M. van der Werf^*, Artem Polyvyanyy, Bart R. van Wensveen, Matthieu J. S. Brinkhuis, Hajo A. Reijers

^*Corresponding author for this work

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

Abstract

The aim of a process discovery algorithm is to construct from event data a process model that describes the underlying, real-world process well. Intuitively, the better the quality of the input event data, the better the quality of the resulting discovered model should be. However, existing process discovery algorithms do not guarantee this relationship. We demonstrate this by using a range of quality measures for both event data and discovered process models. This paper is a call to the community of IS engineers to complement their process discovery algorithms with properties that relate qualities of their inputs to those of their outputs. To this end, we distinguish four incremental stages for the development of such algorithms, along with concrete guidelines for the formulation of relevant properties and experimental validation. We use these stages to reflect on the state of the art, which shows the need to move forward in our thinking about algorithmic process discovery.

Original language	English
Title of host publication	Advanced Information Systems Engineering
Subtitle of host publication	33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings
Editors	Marcello La Rosa, Shazia Sadiq, Ernest Teniente
Publisher	Springer
Pages	141-157
Number of pages	17
Edition	1
ISBN (Electronic)	978-3-030-79382-1
ISBN (Print)	978-3-030-79381-4
DOIs	https://doi.org/10.1007/978-3-030-79382-1_9
Publication status	Published - Jun 2021
Event	33rd International Conference on Advanced Information Systems Engineering, CAiSE 2021 - Virtual, Online Duration: 28 Jun 2021 → 2 Jul 2021

Publication series

Name	Lecture Notes in Computer Science
Volume	12751
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	33rd International Conference on Advanced Information Systems Engineering, CAiSE 2021
City	Virtual, Online
Period	28/06/21 → 2/07/21

Funding

Artem Polyvyanyy was in part supported by the Australian Research Council project DP180102839.

Keywords

Formal guarantees
Process discovery
Process mining
Properties

Access to Document

10.1007/978-3-030-79382-1_9

978-3-030-79382-1_9Final published version, 657 KBLicence: Taverne

Cite this

van der Werf, J. M. E. M., Polyvyanyy, A., van Wensveen, B. R., Brinkhuis, M. J. S., & Reijers, H. A. (2021). All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees. In M. La Rosa, S. Sadiq, & E. Teniente (Eds.), Advanced Information Systems Engineering: 33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings (1 ed., pp. 141-157). (Lecture Notes in Computer Science; Vol. 12751). Springer. https://doi.org/10.1007/978-3-030-79382-1_9

van der Werf, Jan Martijn E.M. ; Polyvyanyy, Artem ; van Wensveen, Bart R. et al. / All that Glitters Is Not Gold : Towards Process Discovery Techniques with Guarantees. Advanced Information Systems Engineering: 33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings. editor / Marcello La Rosa ; Shazia Sadiq ; Ernest Teniente. 1. ed. Springer, 2021. pp. 141-157 (Lecture Notes in Computer Science).

@inproceedings{6dde653ba3eb45b99082fb7e09c03fc2,

title = "All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees",

abstract = "The aim of a process discovery algorithm is to construct from event data a process model that describes the underlying, real-world process well. Intuitively, the better the quality of the input event data, the better the quality of the resulting discovered model should be. However, existing process discovery algorithms do not guarantee this relationship. We demonstrate this by using a range of quality measures for both event data and discovered process models. This paper is a call to the community of IS engineers to complement their process discovery algorithms with properties that relate qualities of their inputs to those of their outputs. To this end, we distinguish four incremental stages for the development of such algorithms, along with concrete guidelines for the formulation of relevant properties and experimental validation. We use these stages to reflect on the state of the art, which shows the need to move forward in our thinking about algorithmic process discovery.",

keywords = "Formal guarantees, Process discovery, Process mining, Properties",

author = "\{van der Werf\}, \{Jan Martijn E.M.\} and Artem Polyvyanyy and \{van Wensveen\}, \{Bart R.\} and Brinkhuis, \{Matthieu J. S.\} and Reijers, \{Hajo A.\}",

year = "2021",

month = jun,

doi = "10.1007/978-3-030-79382-1\_9",

language = "English",

isbn = "978-3-030-79381-4",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "141--157",

editor = "\{La Rosa\}, Marcello and Shazia Sadiq and Ernest Teniente",

booktitle = "Advanced Information Systems Engineering",

edition = "1",

note = "33rd International Conference on Advanced Information Systems Engineering, CAiSE 2021 ; Conference date: 28-06-2021 Through 02-07-2021",

}

van der Werf, JMEM, Polyvyanyy, A, van Wensveen, BR, Brinkhuis, MJS & Reijers, HA 2021, All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees. in M La Rosa, S Sadiq & E Teniente (eds), Advanced Information Systems Engineering: 33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings. 1 edn, Lecture Notes in Computer Science, vol. 12751, Springer, pp. 141-157, 33rd International Conference on Advanced Information Systems Engineering, CAiSE 2021, Virtual, Online, 28/06/21. https://doi.org/10.1007/978-3-030-79382-1_9

All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees. / van der Werf, Jan Martijn E.M.; Polyvyanyy, Artem; van Wensveen, Bart R. et al.
Advanced Information Systems Engineering: 33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings. ed. / Marcello La Rosa; Shazia Sadiq; Ernest Teniente. 1. ed. Springer, 2021. p. 141-157 (Lecture Notes in Computer Science; Vol. 12751).

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

TY - GEN

T1 - All that Glitters Is Not Gold

T2 - 33rd International Conference on Advanced Information Systems Engineering, CAiSE 2021

AU - van der Werf, Jan Martijn E.M.

AU - Polyvyanyy, Artem

AU - van Wensveen, Bart R.

AU - Brinkhuis, Matthieu J. S.

AU - Reijers, Hajo A.

PY - 2021/6

Y1 - 2021/6

N2 - The aim of a process discovery algorithm is to construct from event data a process model that describes the underlying, real-world process well. Intuitively, the better the quality of the input event data, the better the quality of the resulting discovered model should be. However, existing process discovery algorithms do not guarantee this relationship. We demonstrate this by using a range of quality measures for both event data and discovered process models. This paper is a call to the community of IS engineers to complement their process discovery algorithms with properties that relate qualities of their inputs to those of their outputs. To this end, we distinguish four incremental stages for the development of such algorithms, along with concrete guidelines for the formulation of relevant properties and experimental validation. We use these stages to reflect on the state of the art, which shows the need to move forward in our thinking about algorithmic process discovery.

AB - The aim of a process discovery algorithm is to construct from event data a process model that describes the underlying, real-world process well. Intuitively, the better the quality of the input event data, the better the quality of the resulting discovered model should be. However, existing process discovery algorithms do not guarantee this relationship. We demonstrate this by using a range of quality measures for both event data and discovered process models. This paper is a call to the community of IS engineers to complement their process discovery algorithms with properties that relate qualities of their inputs to those of their outputs. To this end, we distinguish four incremental stages for the development of such algorithms, along with concrete guidelines for the formulation of relevant properties and experimental validation. We use these stages to reflect on the state of the art, which shows the need to move forward in our thinking about algorithmic process discovery.

KW - Formal guarantees

KW - Process discovery

KW - Process mining

KW - Properties

UR - https://www.scopus.com/pages/publications/85111175519

U2 - 10.1007/978-3-030-79382-1_9

DO - 10.1007/978-3-030-79382-1_9

M3 - Conference contribution

AN - SCOPUS:85111175519

SN - 978-3-030-79381-4

T3 - Lecture Notes in Computer Science

SP - 141

EP - 157

BT - Advanced Information Systems Engineering

A2 - La Rosa, Marcello

A2 - Sadiq, Shazia

A2 - Teniente, Ernest

PB - Springer

Y2 - 28 June 2021 through 2 July 2021

ER -

van der Werf JMEM, Polyvyanyy A, van Wensveen BR, Brinkhuis MJS , Reijers HA. All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees. In La Rosa M, Sadiq S, Teniente E, editors, Advanced Information Systems Engineering: 33rd International Conference, CAiSE 2021, Melbourne, VIC, Australia, June 28 – July 2, 2021, Proceedings. 1 ed. Springer. 2021. p. 141-157. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-79382-1_9

All that Glitters Is Not Gold: Towards Process Discovery Techniques with Guarantees

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this