Discovering deviating cases and process variants using trace clustering

B.F.A. Hompes, J.C.A.M. Buijs, W.M.P. van der Aalst, P.M. Dixit, J. Buurman

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Uittreksel

Information systems supporting business processes generate event data which provide the starting point for a range of process mining techniques.
Lion's share of real-life processes are complex and ad-hoc, which creates problems for traditional process mining techniques, that cannot deal with such unstructured processes.
Finding mainstream and deviating cases in such data is problematic, since most cases are unique and therefore determining what is normal or exceptional may depend on many factors.
Trace clustering aims to group similar cases in order to find variations of the process and to gain novel insights into the process at hand.
However, few trace clustering techniques take the context of the process into account and focus on the control-flow perspective only.
Outlier detection techniques provide only a binary distinction between normal and exceptional behavior, or depend on a normative process model to be present.
As a result, existing techniques are less suited for processes with a high degree of variability.
In this paper, we introduce a novel trace clustering technique that is able to find process variants as well as deviating behavior based on a set of selected perspectives.
Evaluation on both artificial and real-life event data reveals that additional insights can consequently be achieved.
TaalEngels
Titel27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium
Aantal pagina's8
StatusGepubliceerd - 5 nov 2015
Evenement27th Benelux Conference on Artificial Intelligence (BNAIC 2015) - Hasselt, België
Duur: 5 nov 20156 nov 2015
Congresnummer: 27
http://bnaic2015.org/

Congres

Congres27th Benelux Conference on Artificial Intelligence (BNAIC 2015)
Verkorte titelBNAIC 2015
LandBelgië
StadHasselt
Periode5/11/156/11/15
Internet adres

Vingerafdruk

Flow control
Information systems
Industry

Citeer dit

Hompes, B. F. A., Buijs, J. C. A. M., van der Aalst, W. M. P., Dixit, P. M., & Buurman, J. (2015). Discovering deviating cases and process variants using trace clustering. In 27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium
Hompes, B.F.A. ; Buijs, J.C.A.M. ; van der Aalst, W.M.P. ; Dixit, P.M. ; Buurman, J./ Discovering deviating cases and process variants using trace clustering. 27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium. 2015.
@inproceedings{448f930668684a1590a684a232eaf8c3,
title = "Discovering deviating cases and process variants using trace clustering",
abstract = "Information systems supporting business processes generate event data which provide the starting point for a range of process mining techniques.Lion's share of real-life processes are complex and ad-hoc, which creates problems for traditional process mining techniques, that cannot deal with such unstructured processes.Finding mainstream and deviating cases in such data is problematic, since most cases are unique and therefore determining what is normal or exceptional may depend on many factors.Trace clustering aims to group similar cases in order to find variations of the process and to gain novel insights into the process at hand.However, few trace clustering techniques take the context of the process into account and focus on the control-flow perspective only.Outlier detection techniques provide only a binary distinction between normal and exceptional behavior, or depend on a normative process model to be present.As a result, existing techniques are less suited for processes with a high degree of variability.In this paper, we introduce a novel trace clustering technique that is able to find process variants as well as deviating behavior based on a set of selected perspectives.Evaluation on both artificial and real-life event data reveals that additional insights can consequently be achieved.",
author = "B.F.A. Hompes and J.C.A.M. Buijs and {van der Aalst}, W.M.P. and P.M. Dixit and J. Buurman",
year = "2015",
month = "11",
day = "5",
language = "English",
booktitle = "27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium",

}

Hompes, BFA, Buijs, JCAM, van der Aalst, WMP, Dixit, PM & Buurman, J 2015, Discovering deviating cases and process variants using trace clustering. in 27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium., Hasselt, België, 5/11/15.

Discovering deviating cases and process variants using trace clustering. / Hompes, B.F.A.; Buijs, J.C.A.M.; van der Aalst, W.M.P.; Dixit, P.M.; Buurman, J.

27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium. 2015.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

TY - GEN

T1 - Discovering deviating cases and process variants using trace clustering

AU - Hompes,B.F.A.

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

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

AU - Dixit,P.M.

AU - Buurman,J.

PY - 2015/11/5

Y1 - 2015/11/5

N2 - Information systems supporting business processes generate event data which provide the starting point for a range of process mining techniques.Lion's share of real-life processes are complex and ad-hoc, which creates problems for traditional process mining techniques, that cannot deal with such unstructured processes.Finding mainstream and deviating cases in such data is problematic, since most cases are unique and therefore determining what is normal or exceptional may depend on many factors.Trace clustering aims to group similar cases in order to find variations of the process and to gain novel insights into the process at hand.However, few trace clustering techniques take the context of the process into account and focus on the control-flow perspective only.Outlier detection techniques provide only a binary distinction between normal and exceptional behavior, or depend on a normative process model to be present.As a result, existing techniques are less suited for processes with a high degree of variability.In this paper, we introduce a novel trace clustering technique that is able to find process variants as well as deviating behavior based on a set of selected perspectives.Evaluation on both artificial and real-life event data reveals that additional insights can consequently be achieved.

AB - Information systems supporting business processes generate event data which provide the starting point for a range of process mining techniques.Lion's share of real-life processes are complex and ad-hoc, which creates problems for traditional process mining techniques, that cannot deal with such unstructured processes.Finding mainstream and deviating cases in such data is problematic, since most cases are unique and therefore determining what is normal or exceptional may depend on many factors.Trace clustering aims to group similar cases in order to find variations of the process and to gain novel insights into the process at hand.However, few trace clustering techniques take the context of the process into account and focus on the control-flow perspective only.Outlier detection techniques provide only a binary distinction between normal and exceptional behavior, or depend on a normative process model to be present.As a result, existing techniques are less suited for processes with a high degree of variability.In this paper, we introduce a novel trace clustering technique that is able to find process variants as well as deviating behavior based on a set of selected perspectives.Evaluation on both artificial and real-life event data reveals that additional insights can consequently be achieved.

M3 - Conference contribution

BT - 27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium

ER -

Hompes BFA, Buijs JCAM, van der Aalst WMP, Dixit PM, Buurman J. Discovering deviating cases and process variants using trace clustering. In 27th Benelux Conference on Artificial Intelligence, 5-6 November 2015, Hasselt, Belgium. 2015.