TY  - GEN
AU  - Verenich, I
AU  - Mõškovski, S
AU  - Raboczi, S
AU  - Dumas, M
AU  - La Rosa, M
AU  - Maggi, FM
Y2  - 2018/04/11
Y2  - 2018/04/06
Y2  - 2018/04/06
Y2  - 2018/04/06
Y1  - 2018/06/15
SN  - 978-3-319-92900-2
SN  - 1865-1348
UR  - http://hdl.handle.net/11343/210450
AB  - 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.
PB  - Springer-Verlag, Journals
T1  - Predictive Process Monitoring in Apromore
DO  - 10.1007/978-3-319-92901-9_21
IS  - Lecture Notes in Business Information Processing
IS  - Information Systems in the Big Data Era - Proceedings CAiSE Forum 2018
VL  - 317
SP  - 244-253
OP  - DP180102839
L1  - /bitstream/handle/11343/210450/paper.pdf?sequence=1&isAllowed=y
ER  -