Skip to main content
placeholder image

Goal-aligned categorization of instance variants in knowledge-intensive processes

Journal Article


Abstract


  • Discovering and reasoning about deviations of business process executions (from intended designs) enables organizations to continuously evaluate their execution/performance relative to their strategic goals. We leverage the observation that a deviating process instance can be viewed as a valid variant of the intended process design provided it achieves the same goals as the intended process design. However, organizations often find it difficult to categorize and classify process execution deviations in a goal-based fashion (necessary to decide if a deviation represents a valid variant). Given that industry-scale knowledge-intensive processes typically manifest a large number of variants, this can pose a

    problem. In this paper, we propose an approach to help decide whether process instances in execution logs are valid variants using the goalbased notion of validity described above. Our proposed approach also enables analysis of the impact of contextual factors in the execution of specific goal-aligned process variants.We demonstrate our approach with an Eclipse-based plugin and evaluate it using an industry-scale setting in IT Incident Management with a process log of 25000 events.

UOW Authors


  •   Ponnalagu, Karthikeyan (external author)
  •   Ghose, Aditya
  •   Narendra, Nanjangud C. (external author)
  •   Dam, Hoa

Publication Date


  • 2015

Citation


  • Ponnalagu, K., Ghose, A., Narendra, N. C. & Dam, H. Khanh. (2015). Goal-aligned categorization of instance variants in knowledge-intensive processes. Lecture Notes in Computer Science, 9253 350-364. Innsbruck, Austria Proceedings of the 13th International Conference on Business Process Management

Scopus Eid


  • 2-s2.0-84944691164

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5207

Has Global Citation Frequency


Number Of Pages


  • 14

Start Page


  • 350

End Page


  • 364

Volume


  • 9253

Place Of Publication


  • Germany

Abstract


  • Discovering and reasoning about deviations of business process executions (from intended designs) enables organizations to continuously evaluate their execution/performance relative to their strategic goals. We leverage the observation that a deviating process instance can be viewed as a valid variant of the intended process design provided it achieves the same goals as the intended process design. However, organizations often find it difficult to categorize and classify process execution deviations in a goal-based fashion (necessary to decide if a deviation represents a valid variant). Given that industry-scale knowledge-intensive processes typically manifest a large number of variants, this can pose a

    problem. In this paper, we propose an approach to help decide whether process instances in execution logs are valid variants using the goalbased notion of validity described above. Our proposed approach also enables analysis of the impact of contextual factors in the execution of specific goal-aligned process variants.We demonstrate our approach with an Eclipse-based plugin and evaluate it using an industry-scale setting in IT Incident Management with a process log of 25000 events.

UOW Authors


  •   Ponnalagu, Karthikeyan (external author)
  •   Ghose, Aditya
  •   Narendra, Nanjangud C. (external author)
  •   Dam, Hoa

Publication Date


  • 2015

Citation


  • Ponnalagu, K., Ghose, A., Narendra, N. C. & Dam, H. Khanh. (2015). Goal-aligned categorization of instance variants in knowledge-intensive processes. Lecture Notes in Computer Science, 9253 350-364. Innsbruck, Austria Proceedings of the 13th International Conference on Business Process Management

Scopus Eid


  • 2-s2.0-84944691164

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/5207

Has Global Citation Frequency


Number Of Pages


  • 14

Start Page


  • 350

End Page


  • 364

Volume


  • 9253

Place Of Publication


  • Germany