Software defect prediction method based on class imbalance learning algorithm

Abstract

The invention relates to a software defect prediction method based on a class imbalance learning algorithm. According to the method, a minority class sample is synthesized by using an SWIM oversampling method, so that a data set is converted into moderate imbalance from high imbalance, then minority class misclassification cost most suitable for a current data set is calculated by using a proposedadaptive cost matrix adjustment strategy, and then K weak classifiers are trained according to a training set, so that the classification accuracy of the data set is improved. In the process, the weight of the sample is continuously adjusted, the weight of the wrongly predicted sample is increased, the weight of the correctly predicted sample is reduced, and finally, the K weak classifiers are combined into a composite classifier to predict the category of the to-be-tested sample. According to the method, the problem of low prediction accuracy of minority class samples when the unbalanced data set is predicted is solved, defective modules can be accurately predicted, a test manager is helped to search for defects of software, and the software development cost is reduced.

Description

technical field [0001] The present invention is a learning method for class unbalanced data sets, and aims to use this technology to find defect samples in defect data sets, which can help testers locate defects and allocate test resources more effectively, thereby reducing the cost of software testing , specifically relates to a software defect prediction method based on a class imbalance learning algorithm. Background technique [0002] In the field of software defect prediction, there is a natural class imbalance problem in data sets, that is, in a given data set, the number of instances representing the "defective" class is much less than the number of instances representing the "non-defective" class. However, this defective class is the most important class, and it is the ultimate goal of the classifier to correctly predict samples of the defective class as much as possible. Due to under-representation of defect classes, classification techniques give less weight to in...

AI Technical Summary

Problems solved by technology

In the sample weight adjustment stage, the adaptive cost matrix adjustment strategy is used to assign different misclassification costs to the majority class samples and minority class samples through the cost matrix, and solve the class imbalance problem from the algorithm level

Images