Software defect prediction based on machine learning is an active research topic in the field of software engineering. The historical defect data in software repositories may contain noises because automatic defect collection is based on modified logs and defect reports. When the previous defect labels of modules are limited, predicting the defect‐prone modules becomes a challenging problem. In this study, the authors propose a graph‐based semi‐supervised defect prediction approach to solve the problems of insufficient labelled data and noisy data. Graph‐based semi‐supervised learning methods used the labelled and unlabelled data simultaneously and consider them as the nodes of the graph at the training phase. Therefore, they solve the problem of insufficient labelled samples. To improve the stability of noisy defect data, a powerful clustering method, low‐rank representation (LRR), and neighbourhood distance are used to construct the relationship graph of samples. Therefore, they propose a new semi‐supervised defect prediction approach, named low‐rank representation‐based semi‐supervised software defect prediction (LRRSSDP). The widely used datasets from NASA projects and noisy datasets are employed as test data to evaluate the performance. Experimental results show that (i) LRRSSDP outperforms several representative state‐of‐the‐art semi‐supervised defect prediction methods; and (ii) LRRSSDP can maintain robustness in noisy environments.

Summary Software defect prediction is an important decision support activity in software quality assurance. The limitation of the labelled modules usually makes the prediction difficult, and the class‐imbalance characteristic of software defect data leads to negative influence on decision of classifiers. Semi‐supervised learning can build high‐performance classifiers by using large amount of unlabelled modules together with the labelled modules. Ensemble learning achieves a better prediction capability for class‐imbalance data by using a series of weak classifiers to reduce the bias generated by the majority class. In this paper, we propose a new semi‐supervised software defect prediction approach, non‐negative sparse‐based SemiBoost learning. The approach is capable of exploiting both labelled and unlabelled data and is formulated in a boosting framework. In order to enhance the prediction ability, we design a flexible non‐negative sparse similarity matrix, which can fully exploit the similarity of historical data by incorporating the non‐negativity constraint into sparse learning for better learning the latent clustering relationship among software modules. The widely used datasets from NASA projects are employed as test data to evaluate the performance of all compared methods. Experimental results show that non‐negative sparse‐based SemiBoost learning outperforms several representative state‐of‐the‐art semi‐supervised software defect prediction methods. Copyright © 2016 John Wiley & Sons, Ltd.

In order to improve the quality of a software system, software defect prediction aims to automatically identify defective software modules for efficient software test. To predict software defect, those classification methods with static code attributes have attracted a great deal of attention. In recent years, machine learning techniques have been applied to defect prediction. Due to the fact that there exists the similarity among different software modules, one software module can be approximately represented by a small proportion of other modules. And the representation coefficients over the pre-defined dictionary, which consists of historical software module data, are generally sparse. In this paper, we propose to use the dictionary learning technique to predict software defect. By using the characteristics of the metrics mined from the open source software, we learn multiple dictionaries (including defective module and defective-free module sub-dictionaries and the total dictionary) and sparse representation coefficients. Moreover, we take the misclassification cost issue into account because the misclassification of defective modules generally incurs much higher risk cost than that of defective-free ones. We thus propose a cost-sensitive discriminative dictionary learning (CDDL) approach for software defect classification and prediction. The widely used datasets from NASA projects are employed as test data to evaluate the performance of all compared methods. Experimental results show that CDDL outperforms several representative state-of-the-art defect prediction methods.