Software Defect Prediction based on Machine Learning Algorithms
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 520-525
Abstract
Software defect prediction is very important in software engineering. It uses the defects found in historical software modules to predict defects in new software modules, and provides decision support for planning and process management in software project. Machine learning is one of the core research directions in the field of artificial intelligence and covers many disciplines. In the research of software defect prediction, various machine learning methods have been widely studied and applied, and have been verified to obtain good performance. In this paper, the basic framework of software defect prediction model based on machine learning is described, several important prediction models are studied and discussed. Finally, the main problems of software defect prediction are summarized, and corresponding solutions are proposed.Keywords
This publication has 32 references indexed in Scilit:
- Sample-based software defect prediction with active and semi-supervised learningAutomated Software Engineering, 2011
- Software fault prediction: A literature review and current trendsExpert Systems with Applications, 2011
- Thresholds based outlier detection approach for mining class outliers: An empirical case study on software measurement datasetsExpert Systems with Applications, 2011
- Data clustering: 50 years beyond K-meansPattern Recognition Letters, 2010
- Ensemble-based classifiersArtificial Intelligence Review, 2009
- A systematic review of software fault prediction studiesExpert Systems with Applications, 2009
- On the relative value of cross-company and within-company data for defect predictionEmpirical Software Engineering, 2009
- Analyzing software measurement data with clustering techniquesIEEE Intelligent Systems, 2004
- Naive (Bayes) at forty: The independence assumption in information retrieval1998
- A survey of decision tree classifier methodologyIEEE Transactions on Systems, Man, and Cybernetics, 1991