Using Coding-Based Ensemble Learning to Improve Software Defect Prediction

• Published in: IEEE transactions on human-machine systems 2012-11, Vol.42 (6), p.1806-1817
• Main Authors: Sun, Zhongbin, Song, Qinbao, Zhu, Xiaoyan
• Format: Article
• Language: English
• Subjects: Algorithmics. Computability. Computer arithmetics; Algorithms; Applied sciences; Artificial intelligence; Boosting; Class-imbalance data; Classification; Coding; Computer programs; Computer science; control theory; systems; Computer systems performance. Reliability; Data processing. List processing. Character string processing; Defects; Encoding; Exact sciences and technology; Learning; Memory organisation. Data processing; meta learning; multiclassifier; Prediction algorithms; Predictive models; Sampling; Software; Software algorithms; software defect prediction; Software defects; Studies; Theoretical computing
• ISSN: 1094-6977; 2168-2291; 1558-2442; 2168-2305
• DOI: 10.1109/TSMCC.2012.2226152

Using classification methods to predict software defect proneness with static code attributes has attracted a great deal of attention. The class-imbalance characteristic of software defect data makes the prediction much difficult; thus, a number of methods have been employed to address this problem. However, these conventional methods, such as sampling, cost-sensitive learning, Bagging, and Boosting, could suffer from the loss of important information, unexpected mistakes, and overfitting because they alter the original data distribution. This paper presents a novel method that first converts the imbalanced binary-class data into balanced multiclass data and then builds a defect predictor on the multiclass data with a specific coding scheme. A thorough experiment with four different types of classification algorithms, three data coding schemes, and six conventional imbalance data-handling methods was conducted over the 14 NASA datasets. The experimental results show that the proposed method with a one-against-one coding scheme is averagely superior to the conventional methods.