Software defect prediction model based on LLE and SVM

Software defect prediction strives to improve software security by helping testers locate the software defects accurately. The data redundancy caused by the overmuch attributes in defects data set will make the prediction accuracy decrease. A model based on locally linear embedding and support vector machine (LLE-SVM) is proposed to solve this problem in this paper. The SVM is used as the basic classifier in the model. And the LLE algorithm is used to solve data redundancy due to its ability of maintaining local geometry. The parameters in SVM are optimized by the method of ten-fold cross validation and grid search. The comparison between LLE-SVM model and SVM model was experimentally verified on the same NASA defect data set. The results indicate that the proposal LLE-SVM model performs better than SVM model, and it is available to avoid the accuracy decrease caused by the data redundancy.