Survey on Software Defect Prediction Using Machine Learning Techniques

Software defect prediction plays an important role in improving software quality and it help to reducing time and cost for software testing. Machine learning focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data. The ability of a machine to improve its performance based on previous results. Machine learning improves efficiency of human learning, discover new things or structure that is unknown to humans and find important information in a document. For that purpose, different machine learning techniques are used to remove the unnecessary, erroneous data from the dataset. Software defect prediction is seen as a highly important ability when planning a software project and much greater effort is needed to solve this complex problem using a software metrics and defect dataset. Metrics are the relationship between the numerical value and it applied on the software therefore it is used for predicting defect. The primary goal of this survey paper is to understand the existing techniques for predicting software defect.

[1]  M. SURENDRA NAIDU,et al.  CLASSIFICATION OF DEFECTS IN SOFTWARE USING DECISION TREE ALGORITHM , 2013 .

[2]  Qinbao Song,et al.  Data Quality: Some Comments on the NASA Software Defect Datasets , 2013, IEEE Transactions on Software Engineering.

[3]  Tracy Hall,et al.  Researcher Bias: The Use of Machine Learning in Software Defect Prediction , 2014, IEEE Transactions on Software Engineering.

[4]  Richard Torkar,et al.  Software fault prediction metrics: A systematic literature review , 2013, Inf. Softw. Technol..

[5]  Zsuzsanna Marian,et al.  Detecting software design defects using relational association rule mining , 2013, Knowledge and Information Systems.

[6]  Cagatay Catal,et al.  Software fault prediction: A literature review and current trends , 2011, Expert Syst. Appl..

[7]  Ruchika Malhotra,et al.  Comparative analysis of statistical and machine learning methods for predicting faulty modules , 2014, Appl. Soft Comput..

[8]  Ebru Akcapinar Sezer,et al.  A comparison of some soft computing methods for software fault prediction , 2015, Expert Syst. Appl..

[9]  Xin Peng,et al.  Assessing Software Quality by Program Clustering and Defect Prediction , 2011, 2011 18th Working Conference on Reverse Engineering.

[10]  Andrian Marcus,et al.  An Algorithm for the Discovery of Arbitrary Length Ordinal Association Rules , 2006, DMIN.

[11]  Akito Monden,et al.  A hybrid faulty module prediction using association rule mining and logistic regression analysis , 2008, ESEM '08.

[12]  Bruce Christianson,et al.  Software defect prediction using static code metrics underestimates defect-proneness , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[13]  Cemal Yilmaz,et al.  Software Metrics , 2008, Wiley Encyclopedia of Computer Science and Engineering.

[14]  Olcay Taner Yildiz,et al.  Software defect prediction using Bayesian networks , 2012, Empirical Software Engineering.