A Web Tool for the Comparison of Predictive Process Monitoring Algorithms
Name
Ayham Taleb
Abstract
Predictive Process Monitoring analyzes an event log aiming to predict critical business metrics as time, cost and process outcomes. Various techniques and approaches of predictions were developed in both academia and industry sectors in order to provide understandable predictions to the users. In this Master’s Thesis, we introduce a web based tool for the comparison of predictive process monitoring algorithms which provides researchers or end users involved in this field an easier way for choosing the suitable prediction approach to a certain log. This project uses a queuing system which is able to build different predictive models at the same time. We show the results of different predictive models with a visual comparison that allows the evaluation of each predictive model. The new functionalities have been implemented in a web application, which allows users to configure and trigger the tasks of the queuing system and shows the results. The application has been evaluated on a real-life log pertaining to the treatment process of sepsis patients in a hospital.
Graduation Thesis language
English
Graduation Thesis type
Master - Software Engineering
Supervisor(s)
Fabrizio Maria Maggi, Fredrik Payman Milani
Defence year
2017