Learning from the good and the bad: Diagnosis and prediction of Business Process Deviances
Project Leader: Marcello La Rosa
Staff: Marcello La Rosa, Artem Polyvyanyy
Collaborators: Wil van der Aalst, Marlon Dumas
Sponsors: Australian Research Council
Primary Contact: Artem Polyvyanyy (firstname.lastname@example.org)
Keywords: business process management; machine learning; process mining
Disciplines: Computing and Information Systems
This project aims to develop an innovative approach to analyse process execution data (event logs) logged by IT systems in order to diagnose and predict business process deviance. Anticipated outcomes include novel business intelligence algorithms producing deviance diagnostics, predictions and recommendations and exposing results via interactive visual analytics. The outcomes are expected to aid process workers in steering business operations towards consistent and compliant outcomes and higher performance, and assist analysts and auditors to explain deviant operations. This is expected to provide benefits to all those industries where compliance and integrity management are critical capabilities, including healthcare, insurance, retail and the government where compliance and integrity management are imperative.
Concrete outcomes of the project will depend on the specific path the project will follow and may include new techniques, algorithms, and methodologies for diagnosis and prediction of business process deviances.
The outcomes of this project will be implemented in the form of plugins for the open-source technology Apromore (http://apromore.org). The envisaged technology will exploit information hidden in event logs to support companies in understanding when, how and why their business processes deviate from prescribed or expected pathways.
- 2 PhD positions (3 years each, scholarship and tuition fee waiver included), and
- 2 Research Fellow (Postdoc) positions for 2 years each, extensible to 3 years. Please apply here. Applications close: 26 Jul 2018 11:55 PM AUS Eastern Standard Time.
REQUIRED SKILLS: knowledge of process mining/machine learning, programming (Java, Python/R).
DESIRED SKILLS: knowledge of deep learning and active learning algorithms.
WORKING HOURS: 2 Full-Time Postdocs and 2 Full-Time PhD students.
LOCATION: Parkville, University of Melbourne.
HOW TO APPLY: Contact Prof Marcello La Rosa (email@example.com) for further details.