Tell me what’s ahead? Predicting remaining activity sequences of business process instances

Verenich, Ilya, Dumas, Marlon, La Rosa, Marcello, Maggi, Fabrizio Maria, Chasovskyi, Dmytro, & Rozumnyi, Andrii (2016) Tell me what’s ahead? Predicting remaining activity sequences of business process instances.

Abstract

Predictive business process monitoring is a family of techniques to determine how running instances of a business process are likely to unfold in the future. Techniques in this space differ according to their object of prediction. Some predict whether or not a running process instance will fulfill a compliance rule, others predict whether or not a given activity will occur, while others predict the remaining execution time. These and other predictive process monitoring problems are subsumed by the problem of predicting the remaining sequence of activities of a given process instance.

In this paper, we tackle this latter problem using two alternative approaches. In the first one, we statically construct a transition system from an event log of completed process instances and annotate each transition with a probability calculated using a k-nearest neighbors classifier. At runtime, we map the (incomplete) trace of a process instance to a state in the transition system. To predict the remaining activity sequence of a process instance, we calculate a highest-probability path starting from the current state. In the second approach, we treat the problem of activity sequence prediction as a structured output prediction problem and apply recurrent neural networks. The accuracy of the two proposed approaches is evaluated on real-life and synthetic datasets and compared against an existing baseline technique.

Impact and interest:

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

69 since deposited on 10 Jul 2016
69 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 96732
Item Type: Report
Refereed: No
Keywords: process mining, predictive monitoring, structured prediction, sequence classification
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > INFORMATION SYSTEMS (080600)
Divisions: Current > Schools > School of Information Systems
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2016 The Author(s)
Deposited On: 10 Jul 2016 22:55
Last Modified: 11 Jul 2016 09:08

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page