Intelligent process mining and optimization
No Thumbnail Available
URL
Journal Title
Journal ISSN
Volume Title
School of Business |
Bachelor's thesis
Electronic archive copy is available locally at the Harald Herlin Learning Centre. The staff of Aalto University has access to the electronic bachelor's theses by logging into Aaltodoc with their personal Aalto user ID. Read more about the availability of the bachelor's theses.
Authors
Date
2021
Department
Major/Subject
Mcode
Degree programme
Tieto- ja palvelujohtaminen
Language
en
Pages
33
Series
Abstract
The continuous and rapid development of information technologies and systems has enabled organizations to gather data in a more detailed level of the executed actions between virtual and physical environments, allowing organizations to explore executed tasks and processes more precisely. As digital transformation has become a major theme across industries, organizations have started to find ways to utilize this gathered data in a more efficient manner. This has rapidly affected the development of process mining, where the aim is to discover bottlenecks and deviations from the data created by information systems. This thesis is conducted as a literature review aiming to provide a summary of the developed approaches in the field of process mining. As the vast majority of the previously conducted studies have addressed the traditional process mining methods, the primary objective of this thesis is to provide a summary of the currently available approaches of process mining and currently available applications of Artificial Intelligence (AI), Machine Learning (ML), and Robotic Process Automation (RPA) in process mining. The focus is especially on how these technologies can be used in process mining, and what kind of intelligent predictions these technologies can create. Findings of the literature review clearly shows that the growing popularity has positively affected to development of predictive process mining algorithms especially in the process discovery phase. By using AI and ML in the discovery phase, the data converting, and visualizing can be done in a more structured and classified manner. When combining AI, ML and RPA as an integrated part of traditional process discovery tools, organizations can discover valuable predictive insights of the process delays, outcomes, next steps, and parts of the process that would be beneficial to automate. However, previously conducted studies did not show any applications of AI, ML, or RPA in the context of process optimization, which is why this thesis suggests that future research would address the automation of process optimization based on the predictions.Description
Thesis advisor
Bragge, JohannaKeywords
process mining, process optimization, artificial intelligence, predictive business process monitoring