Business Process Automation: Automating the Analysis of Anomaly Data

- This research proposes a method which evaluates a real-world data analytics business process to identify key performance variables for the manual business process. Once complete, we incorporate these finding to an unsupervised machine learning algorithm to allow for tuning of the outputs. Experiments show that using this approach can reduce the overall number of undesired outputs, giving an overall higher effectiveness for the ML system in a real-world application. The proposed method offers consistency while providing an organization the option of focusing resources on high value activities.