Software defect prediction with imbalanced distribution by radius‐synthetic minority over‐sampling technique

Abstract

Software defect prediction, which can identify the defect-prone modules, is an effective technology to ensure the quality of software products. Due to the importance in software maintenance, many learning-based software defect prediction models are presented in recent years. Actually, the defects usually occupy a very small proportions in software source codes; thus, the imbalanced distributions between defectprone modules and non-defect-prone modules increase the learning difficulty of the classification task. To address this issue, we present a random over-sampling mechanism used to generate minority-class samples from high-dimensional sampling space to deal with the imbalanced distributions in software defect prediction, in which two constraints are applied to provide a robust way to generate new synthetic samples, that is, scaling the random over-sampling scope to a reasonable area and distinguishing the majority-class samples in a critical region. Based on nine open datasets of software projects, we experimentally verify that our presented method is effective on predict the defect-prone modules, and the effect is superior to the traditional imbalanced processing methods.

Software Defect Prediction Approaches Revisited

“…COSTE boosts data diversity, keeps prediction models' ability to identify flaws, and considers the variable testing effort required in various instances. To address the unequal distributions in the SDP, the authors of [20] introduced a mechanism for generating samples for the minority class from a high-dimensional sampling space using random over-sampling. Two restrictions are applied to this mechanism to provide a reliable method for creating new synthetic samples, which involves narrowing the range of random oversampling and differentiating the majority-class samples in key areas.…”

“…Probability of Detection, False Positive Rate, G-mean [20] Radius Synthetic Minority Over-sampling Technique (RSMOTE) Recall, Precision, F-measure [15] An innovative Class Imbalance Reduction (CIR) algorithm for creating new samples is based on determining the centroid of all attributes of minority-class samples.…”

WIFLF: An approach independent of the target project for cross‐project defect prediction

“…SDP predicts defects (aka bugs) situation in software system via machine learning techniques and assists on resource allocation of software testing 3–5,28,29 . In engineering practice, researchers focus on different aspects of SDP.…”

“…2.1 | Software defect prediction SDP predicts defects (aka bugs) situation in software system via machine learning techniques and assists on resource allocation of software testing. [3][4][5]28,29 In engineering practice, researchers focus on different aspects of SDP. For different prediction tasks, SDP includes binary classification, 17,18,21,24,[29][30][31][32] numeric, 1,33,34 ranking, 35,36 and association rule mining.…”

“…[3][4][5]28,29 In engineering practice, researchers focus on different aspects of SDP. For different prediction tasks, SDP includes binary classification, 17,18,21,24,[29][30][31][32] numeric, 1,33,34 ranking, 35,36 and association rule mining. 37,38 According to different sources of training data, SDP can be divided into three scenarios: WPDP, CPDP, and mixed-project defect prediction (MPDP).…”