ProDiGy: Human-in-the-loop process discovery

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)
1 Downloads (Pure)

Abstract

Process mining is a discipline that combines the two worlds of business process management and data mining. The central component of process mining is a graphical process model that provides an intuitive way of capturing the logical flow of a process. Traditionally, these process models are either modeled by a user relying on domain expertise only; or discovered automatically by relying entirely on event data. In an attempt to address this apparent gap between user-driven and data-driven process discovery, we present ProDiGy, an alternative approach that enables interactive process discovery by allowing the user to actively steer process discovery. ProDiGy provides the user with automatic recommendations to edit a process model, and quantify and visualize the impact of each recommendation. We evaluated ProDiGy (i) objectively by comparing it with automated discovery approaches and (ii) subjectively by performing a user study with healthcare researchers. Our results show that ProDiGy enables inclusion of domain knowledge in process discovery, which leads to an improvement of the results over the traditional process discovery techniques. Furthermore, we found that ProDiGy also increases the comprehensibility of a process model by providing the user with more control over the discovery of the process model.

Original languageEnglish
Title of host publication2018 12th International Conference on Research Challenges in Information Science, RCIS 2018
Place of PublicationPiscataway
PublisherIEEE Computer Society
Pages1-12
Number of pages12
ISBN (Electronic)978-1-5386-6517-6
DOIs
Publication statusPublished - 6 Jul 2018
Event12th International Conference on Research Challenges in Information Science, RCIS 2018 - Nantes, France
Duration: 29 May 201831 May 2018

Conference

Conference12th International Conference on Research Challenges in Information Science, RCIS 2018
CountryFrance
CityNantes
Period29/05/1831/05/18

Fingerprint

Data mining
Industry

Keywords

  • Interactive Process Mining
  • User Driven Process Discovery

Cite this

Dixit, P. M., Buijs, J. C. A. M., & van der Aalst, W. M. P. (2018). ProDiGy: Human-in-the-loop process discovery. In 2018 12th International Conference on Research Challenges in Information Science, RCIS 2018 (pp. 1-12). Piscataway: IEEE Computer Society. https://doi.org/10.1109/RCIS.2018.8406657
Dixit, P.M. ; Buijs, J.C.A.M. ; van der Aalst, W.M.P. / ProDiGy : Human-in-the-loop process discovery. 2018 12th International Conference on Research Challenges in Information Science, RCIS 2018. Piscataway : IEEE Computer Society, 2018. pp. 1-12
@inproceedings{b425af5e17524b61917ec7e3e6202b20,
title = "ProDiGy: Human-in-the-loop process discovery",
abstract = "Process mining is a discipline that combines the two worlds of business process management and data mining. The central component of process mining is a graphical process model that provides an intuitive way of capturing the logical flow of a process. Traditionally, these process models are either modeled by a user relying on domain expertise only; or discovered automatically by relying entirely on event data. In an attempt to address this apparent gap between user-driven and data-driven process discovery, we present ProDiGy, an alternative approach that enables interactive process discovery by allowing the user to actively steer process discovery. ProDiGy provides the user with automatic recommendations to edit a process model, and quantify and visualize the impact of each recommendation. We evaluated ProDiGy (i) objectively by comparing it with automated discovery approaches and (ii) subjectively by performing a user study with healthcare researchers. Our results show that ProDiGy enables inclusion of domain knowledge in process discovery, which leads to an improvement of the results over the traditional process discovery techniques. Furthermore, we found that ProDiGy also increases the comprehensibility of a process model by providing the user with more control over the discovery of the process model.",
keywords = "Interactive Process Mining, User Driven Process Discovery",
author = "P.M. Dixit and J.C.A.M. Buijs and {van der Aalst}, W.M.P.",
year = "2018",
month = "7",
day = "6",
doi = "10.1109/RCIS.2018.8406657",
language = "English",
pages = "1--12",
booktitle = "2018 12th International Conference on Research Challenges in Information Science, RCIS 2018",
publisher = "IEEE Computer Society",
address = "United States",

}

Dixit, PM, Buijs, JCAM & van der Aalst, WMP 2018, ProDiGy: Human-in-the-loop process discovery. in 2018 12th International Conference on Research Challenges in Information Science, RCIS 2018. IEEE Computer Society, Piscataway, pp. 1-12, 12th International Conference on Research Challenges in Information Science, RCIS 2018, Nantes, France, 29/05/18. https://doi.org/10.1109/RCIS.2018.8406657

ProDiGy : Human-in-the-loop process discovery. / Dixit, P.M.; Buijs, J.C.A.M.; van der Aalst, W.M.P.

2018 12th International Conference on Research Challenges in Information Science, RCIS 2018. Piscataway : IEEE Computer Society, 2018. p. 1-12.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - ProDiGy

T2 - Human-in-the-loop process discovery

AU - Dixit, P.M.

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

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

PY - 2018/7/6

Y1 - 2018/7/6

N2 - Process mining is a discipline that combines the two worlds of business process management and data mining. The central component of process mining is a graphical process model that provides an intuitive way of capturing the logical flow of a process. Traditionally, these process models are either modeled by a user relying on domain expertise only; or discovered automatically by relying entirely on event data. In an attempt to address this apparent gap between user-driven and data-driven process discovery, we present ProDiGy, an alternative approach that enables interactive process discovery by allowing the user to actively steer process discovery. ProDiGy provides the user with automatic recommendations to edit a process model, and quantify and visualize the impact of each recommendation. We evaluated ProDiGy (i) objectively by comparing it with automated discovery approaches and (ii) subjectively by performing a user study with healthcare researchers. Our results show that ProDiGy enables inclusion of domain knowledge in process discovery, which leads to an improvement of the results over the traditional process discovery techniques. Furthermore, we found that ProDiGy also increases the comprehensibility of a process model by providing the user with more control over the discovery of the process model.

AB - Process mining is a discipline that combines the two worlds of business process management and data mining. The central component of process mining is a graphical process model that provides an intuitive way of capturing the logical flow of a process. Traditionally, these process models are either modeled by a user relying on domain expertise only; or discovered automatically by relying entirely on event data. In an attempt to address this apparent gap between user-driven and data-driven process discovery, we present ProDiGy, an alternative approach that enables interactive process discovery by allowing the user to actively steer process discovery. ProDiGy provides the user with automatic recommendations to edit a process model, and quantify and visualize the impact of each recommendation. We evaluated ProDiGy (i) objectively by comparing it with automated discovery approaches and (ii) subjectively by performing a user study with healthcare researchers. Our results show that ProDiGy enables inclusion of domain knowledge in process discovery, which leads to an improvement of the results over the traditional process discovery techniques. Furthermore, we found that ProDiGy also increases the comprehensibility of a process model by providing the user with more control over the discovery of the process model.

KW - Interactive Process Mining

KW - User Driven Process Discovery

UR - http://www.scopus.com/inward/record.url?scp=85050894036&partnerID=8YFLogxK

U2 - 10.1109/RCIS.2018.8406657

DO - 10.1109/RCIS.2018.8406657

M3 - Conference contribution

AN - SCOPUS:85050894036

SP - 1

EP - 12

BT - 2018 12th International Conference on Research Challenges in Information Science, RCIS 2018

PB - IEEE Computer Society

CY - Piscataway

ER -

Dixit PM, Buijs JCAM, van der Aalst WMP. ProDiGy: Human-in-the-loop process discovery. In 2018 12th International Conference on Research Challenges in Information Science, RCIS 2018. Piscataway: IEEE Computer Society. 2018. p. 1-12 https://doi.org/10.1109/RCIS.2018.8406657