Thesis Defense - Mustafa Gökçeoğlu (MSCS)

Mustafa Gökçeoğlu - M.Sc. Computer Science

Assoc.Prof. Hasan Sözer – Advisor

Date: 14.01.2021

Time: 10:00

Location: This meeting will be held ONLINE. Please send an e-mail to gizem.bakir@ozyegin.edu.tr in order to participate in this defense.

Automated Defect Prioritization based on Defects Resolved at Various Project Phases

Thesis Committee:

Assoc.Prof. Hasan Sözer, Özyeğin University

Asst.Prof. Furkan Kıraç, Özyeğin University

Prof. Oya Kalıpsız, Yildiz Technical University

Abstract:

Defect prioritization is mainly a manual and error-prone task in the current state-of-the-practice. We evaluated the effectiveness of an automated approach that employs supervised machine learning. We used two alternative techniques, namely a Naive Bayes classifier and a Long Short-Term Memory model. We performed an industrial case study with a real project from the consumer electronics domain. We compiled more than 15,000 issues collected over 3 years. We could reach an accuracy level up to 79.36% and we had 3 observations. First, the Long Short-Term Memory model has better accuracy when compared with a Naive Bayes classifier. Second, structured features lead to better accuracy compared to textual descriptions. Third, accuracy is not improved by considering increasingly earlier defects as part of the training data. Increasing the size of the training data even decreases the accuracy compared to the results, when we use data only regarding the recent defects reported in the previous phase of the project.

Bio: 

Mustafa Gökçeoğlu graduated from Istanbul Technical University in Computer Engineering in 2017. After graduation, he worked in Vestel Electronics as a software engineer at the TV R/D System Software. At the same time, he started to Ozyegin University Msc program while working in Vestel Electronics. In 2019, he becomes a senior software specialist in Vestel Electronics, where he is currently working.