Predictive Process Monitoring in Apromore

Download
Author
Verenich, I; Mõškovski, S; Raboczi, S; Dumas, M; La Rosa, M; Maggi, FMDate
2018-06-15Source Title
Lecture Notes in Business Information ProcessingPublisher
Springer-Verlag, JournalsAffiliation
Computing and Information SystemsMetadata
Show full item recordDocument Type
Conference PaperCitations
Verenich, I., Mõškovski, S., Raboczi, S., Dumas, M., La Rosa, M. & Maggi, F. M. (2018). Predictive Process Monitoring in Apromore. Lecture Notes in Business Information Processing, 317, pp.244-253. Springer-Verlag, Journals. https://doi.org/10.1007/978-3-319-92901-9_21.Access Status
Open AccessARC Grant code
ARC/DP180102839Abstract
This paper discusses the integration of Nirdizati, a tool for predictive process monitoring, into the Web-based process analytics platform Apromore. Through this integration, Apromore’s users can use event logs stored in the Apromore repository to train a range of predictive models, and later use the
trained models to predict various performance indicators of running process cases from a live event stream. For example, one can predict the remaining time or the next events until case completion, the case outcome, or the violation of compliance rules or internal policies. The predictions can be presented graphically via a dashboard that offers multiple visualization options, including a range of summary statistics about ongoing and past process cases. They can also be exported into CSV for periodic reporting or to be visualized in third-parties business intelligence tools. Based on these predictions, operations managers may identify potential issues early on, and take remedial actions in a timely fashion, e.g. reallocating resources from one case onto another to avoid that the case runs overtime.
Export Reference in RIS Format
Endnote
- Click on "Export Reference in RIS Format" and choose "open with... Endnote".
Refworks
- Click on "Export Reference in RIS Format". Login to Refworks, go to References => Import References