A Comparision of GNNs and LSTMs for Process Mining Applications

Aayam KHADKA

Diplomová práce

Abstract:

The research question focuses on the comparative analysis of two models, GCN and multi-task LSTM regarding event log data of high-level processes. Order to Cash, and Purchase to Pay in process mining. The study aims to evaluate the implementation of these models in future event prediction and time prediction. High-level processes such as Order to Cash, and Purchase to Pay event log data may contain redundancy, and irregularities that are crucial for an organization therefore the research aims to provide valuable insights into the effectiveness of deep learning methods in the predictive performance of event and timestamp.

Keywords

Event logs, Process Mining, Deep learning, Machine learning

Jazyk práce: angličtina

Datum vytvoření / odevzdání či podání práce: 8. 2. 2024

Obhajoba závěrečné práce

• Vedoucí: Markus Eider, M.Sc.

JIHOČESKÁ UNIVERZITA V ČESKÝCH BUDĚJOVICÍCH

Přírodovědecká fakulta

Magisterský studijní program / obor:
Artificial Intelligence and Data Science / Artificial Intelligence and Data Science