A Novel Approach to Improve Software Defect Prediction Accuracy Using Machine Learning

In software engineering community, defect prediction is one the active domain. For software’s success, it essential to reduce and data-mining gap. Software defects forecasts source code errors before testing phase. Methods for predicting defects, such as clustering, statistical methods, mixed algorithms, metrics based on neural networks, black box testing, white machine learning are frequently used explore effect area in software. The main contribution of this research use feature selection first time increase accuracy classifiers pre-diction. objective study improve five data sets NASA namely; CM1, JM1, KC2, KC1, PC1. These open public. research, technique with machine-learning techniques; Random Forest, Logistic Regression, Multilayer Perceptron, Bayesian Net, Rule ZeroR, J48, Lazy IBK, Support Vector Machine, Neural Networks, Decision Stump achieve high compared without (WOFS). workbench, a tool called WEKA (Waikato Environment Knowledge Analysis), refine da-ta, preprocess data, apply mentioned classifiers. To assess analyses, mini tab used. results reveals that (WFS) contrast WOFS.