| dc.description.abstract | This thesis aims to address the challenges faced by two businesses, an automated parking system provider and a public transport operator, in managing and resolving system failures. The current manual approach of recording and classifying defects using Excel sheets leads to inefficiencies and potential misclassification. The research focuses on utilizing machine learning algorithms to categorize reported bugs in a labeled dataset and evaluate the accuracy of the existing bug classification system. Various supervised machine learning models, including SVM, logistic regression, and decision tree classifier, are trained and compared. Unsupervised machine learning methods are also employed to analyze and categorize failures in an unlabeled dataset. The findings of this research will help improve the bug classification and issue resolution procedures, leading to enhanced dependability and client satisfaction for the businesses. | |