A Review on Machine Learning Techniques for Software Defect Prediction

Main Article Content

Fareeha Hassan
Saima Farhan
Muhammad Abuzar Fahiem
Huma Tauseef

Abstract

Software defect prediction has been an interest of research era because predicting defects on early stages improves software quality with reduced cost and effective software management. Researchers from different domains are contributing their efforts to propose an approach that effectively and efficiently helps in this regard. Different machine learning techniques have been applied to remove unnecessary and fault data from defect prone modules and many approaches, frameworks, methods and models have been proposed using different datasets, metrics, and evaluation strategies. In this paper, 30 Clarivate Analytics indexed journal papers from 2009-2017 are reviewed for the upcoming practitioners of software defect prediction. Review in this paper reflects some of the work that has been done in software defect prediction so far. Detailed classification taxonomy of the machine learning techniques used for software defect prediction has been presented. Defective, non-defective datasets along with the classification of the metrics used are part of the review. Despite of all works and efforts done in this research domain, there still exist many ambiguities because no single technique and method dominates due to the imbalance nature of different datasets and methods. A lot of research work is needed to overcome the existing issues.

Article Details

Section
COMPUTER SCIENCE
Author Biographies

Fareeha Hassan, Lahore College for Women University

Department of Computer Science

Saima Farhan, Lahore College for Women University

Assistant Professor, Department of Computer Science

Muhammad Abuzar Fahiem, Lahore College for Women University

Head of Department & Associate Professor, Department of Computer Science

Huma Tauseef, Lahore College for Women University

Assistant Professor, Department of Computer Science