Adaptive Business Process Analysis Using Machine Learning Algorithms

Sterie, Radu (2023) Adaptive Business Process Analysis Using Machine Learning Algorithms. Bachelor's Thesis, Computing Science.

Preview	Text bCS_2023_SterieRA.pdf Download (3MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (217kB)

Abstract

This undergraduate research delves into the application of machine learning to uncover correlations in adaptive business process logs. Utilizing innovative techniques, the study analyzes data through algorithms like Generalized Learning Vector Quantization (GLVQ), K-Nearest Neighbors (KNN), Decision Trees, and Random Forest. The aim is to discern inherent patterns and extract pertinent adaptations from the logs. Two custom programs, NEXT(LOG) and ML.LOG, were employed—the former generates logs based on set rules, while the latter extracts these rules. Machine learning models were trained using diverse parameters and evaluated using metrics like F1 score, recall, and accuracy. The results revealed that Decision Trees and Random Forests were most effective in rule extraction. Despite its limitations, such as a restricted range of machine learning models, this approach holds potential for future research. The study contributes to the growing realm of machine learning in business process analysis, detailing the methodology, model outcomes, extracted rules, and the implications of these discoveries. The insights are expected to inspire further exploration in adaptive business process analysis.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Yadegari Ghahderijani, A. and Karastoyanova, D.
Degree programme:	Computing Science
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	14 Aug 2023 09:38
Last Modified:	14 Aug 2023 09:38
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/31141

Actions (login required)

View Item