Optimizing bug prediction in software testing using Super Learner

Nair, Prajeeth Raghunath (2019) Optimizing bug prediction in software testing using Super Learner. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

Software testing is a crucial part of every software project to ensure that the applications delivered to the end-users are defect-free and reliable. Mining of software repositories can uncover useful software metrics which can aid in the early detection of bugs through software fault prediction. This information can be utilized by software project managers to handle resource allocation and optimize the testing process effectively. This paper proposes a novel super learner classification technique for predicting bug-prone modules in the software. The base learners for the classifier comprises of Support Vector Machine (SVM), Decision Tree, Logistic Regression (LR), and the meta learner used is Extreme Gradient Boosting (XGBoost). The experiment is carried out on publicly available datasets from PROMISE repository and Eclipse bug prediction dataset. The results show that by combining the predictions of multiple base learners, the presented Super learner provides a robust and generalized performance compared to the individual classifiers for predicting bugs in software.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	11 Oct 2019 15:22
Last Modified:	11 Oct 2019 15:22
URI:	https://norma.ncirl.ie/id/eprint/3853

Actions (login required)

View Item