Software defect prediction method, system and equipment based on balanced subset and medium

Abstract

The embodiment of the invention provides a software defect prediction method, system and device based on a balanced subset and a medium, and belongs to the technical field of data processing, and the method specifically comprises the steps that an unbalanced data set generated in the operation process of target software is obtained, and the unbalanced data set comprises an original multi-class set and an original few-class set; randomly dividing the original multi-class set XN into V subclasses with the same sample number; according to a division instruction input by a user, different division strategies are selected, and the division strategy is any one of a balance subset construction strategy based on random division or a balance subset construction strategy based on hierarchical division; and according to the division strategy, all the subclasses and the original few-class set, constructing V balanced subsets corresponding to the unbalanced data set, and carrying out ensemble learning to obtain the defect class of the target software. According to the scheme of the invention, all original samples are reserved, no new sample is introduced, and the classification performance and the prediction accuracy are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of data processing, and in particular, to a method, system, device, and medium for predicting software defects based on balanced subsets. Background technique [0002] Common software defect prediction methods assume that all classes in the dataset are balanced, that is, the sample sizes are roughly equal. However, in the actual running process of software, there are often more defects than those without defects. The imbalance problem is widely regarded as one of the main reasons for the poor performance of software defect prediction models. Therefore, it is necessary to construct a software defect prediction model based on imbalanced data. [0003] In recent years, various data rebalancing methods for software defect prediction have been proposed. Although some of them achieve better performance, they have the following shortcomings: [0004] For upsampling methods, they need to sy...

AI Technical Summary

Problems solved by technology

[0008] In view of this, the embodiments of the present invention provide a software defect prediction method, system, device, and medium based on balanced subsets, which at least partially solve the problems of low prediction accuracy and poor efficiency in the prior art

Images