Aarhus University Seal

Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones. / Bloemen, Vincent; Zelst, Sebastiaan van; Aalst, Wil van der et al.

In: Information Systems, Vol. 103, 101456, 01.2022.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

Bloemen, V., Zelst, S. V., Aalst, W. V. D., Dongen, B. V., & Pol, J. V. D. (2022). Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones. Information Systems, 103, [101456]. https://doi.org/10.1016/j.is.2019.101456

CBE

MLA

Vancouver

Bloemen V, Zelst SV, Aalst WVD, Dongen BV, Pol JVD. Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones. Information Systems. 2022 Jan;103:101456. Epub 2019 Oct 26. doi: 10.1016/j.is.2019.101456

Author

Bloemen, Vincent ; Zelst, Sebastiaan van ; Aalst, Wil van der et al. / Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones. In: Information Systems. 2022 ; Vol. 103.

Bibtex

@article{cd2924fbdcf34b22abb4fa828f1aa07f,
title = "Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones",
abstract = "Given a process model and an event log, conformance checking aims to relate the two together, e.g. to detect discrepancies between them. For the synchronous product net of the process and a log trace, we can assign different costs to a synchronous move, and a move in the log or model. By computing a path through this (synchronous) product net, whilst minimizing the total cost, we create a so-called optimal alignment — which is considered to be the primary target result for conformance checking. Traditional alignment-based approaches (1) have performance problems for larger logs and models, and (2) do not provide reliable diagnostics for non-conforming behaviour (e.g. bottleneck analysis is based on events that did not happen). This is the reason to explore an alternative approach that maximizes the use of observed events. We also introduce the notion of milestone activities, i.e. unskippable activities, and show how the different approaches relate to each other. We propose a data structure, that can be computed from the process model, which can be used for (1) computing alignments of many log traces that maximize synchronous moves, and (2) as a means for analysing non-conforming behaviour. In our experiments we show the differences of various alignment cost functions. We also show how the performance of constructing alignments with our data structure relates to that of the state-of-the-art techniques.",
keywords = "Alignment cost function, Alignments, Conformance checking, Milestone events, Process mining, Transitive closure graph",
author = "Vincent Bloemen and Zelst, {Sebastiaan van} and Aalst, {Wil van der} and Dongen, {Boudewijn van} and Pol, {Jaco van de}",
year = "2022",
month = jan,
doi = "10.1016/j.is.2019.101456",
language = "English",
volume = "103",
journal = "Information Systems",
issn = "0306-4379",
publisher = "Elsevier Ltd",

}

RIS

TY - JOUR

T1 - Aligning observed and modelled behaviour by maximizing synchronous moves and using milestones

AU - Bloemen, Vincent

AU - Zelst, Sebastiaan van

AU - Aalst, Wil van der

AU - Dongen, Boudewijn van

AU - Pol, Jaco van de

PY - 2022/1

Y1 - 2022/1

N2 - Given a process model and an event log, conformance checking aims to relate the two together, e.g. to detect discrepancies between them. For the synchronous product net of the process and a log trace, we can assign different costs to a synchronous move, and a move in the log or model. By computing a path through this (synchronous) product net, whilst minimizing the total cost, we create a so-called optimal alignment — which is considered to be the primary target result for conformance checking. Traditional alignment-based approaches (1) have performance problems for larger logs and models, and (2) do not provide reliable diagnostics for non-conforming behaviour (e.g. bottleneck analysis is based on events that did not happen). This is the reason to explore an alternative approach that maximizes the use of observed events. We also introduce the notion of milestone activities, i.e. unskippable activities, and show how the different approaches relate to each other. We propose a data structure, that can be computed from the process model, which can be used for (1) computing alignments of many log traces that maximize synchronous moves, and (2) as a means for analysing non-conforming behaviour. In our experiments we show the differences of various alignment cost functions. We also show how the performance of constructing alignments with our data structure relates to that of the state-of-the-art techniques.

AB - Given a process model and an event log, conformance checking aims to relate the two together, e.g. to detect discrepancies between them. For the synchronous product net of the process and a log trace, we can assign different costs to a synchronous move, and a move in the log or model. By computing a path through this (synchronous) product net, whilst minimizing the total cost, we create a so-called optimal alignment — which is considered to be the primary target result for conformance checking. Traditional alignment-based approaches (1) have performance problems for larger logs and models, and (2) do not provide reliable diagnostics for non-conforming behaviour (e.g. bottleneck analysis is based on events that did not happen). This is the reason to explore an alternative approach that maximizes the use of observed events. We also introduce the notion of milestone activities, i.e. unskippable activities, and show how the different approaches relate to each other. We propose a data structure, that can be computed from the process model, which can be used for (1) computing alignments of many log traces that maximize synchronous moves, and (2) as a means for analysing non-conforming behaviour. In our experiments we show the differences of various alignment cost functions. We also show how the performance of constructing alignments with our data structure relates to that of the state-of-the-art techniques.

KW - Alignment cost function

KW - Alignments

KW - Conformance checking

KW - Milestone events

KW - Process mining

KW - Transitive closure graph

UR - http://www.scopus.com/inward/record.url?scp=85081296323&partnerID=8YFLogxK

U2 - 10.1016/j.is.2019.101456

DO - 10.1016/j.is.2019.101456

M3 - Journal article

VL - 103

JO - Information Systems

JF - Information Systems

SN - 0306-4379

M1 - 101456

ER -