HIGH ACCURACY PREDICTION ON SOFTWARE DEFECT DATASETSUSINGAVERAGE PROBABILITY ENSEMBLE TECHNIQUE

Abstract

The present generation software testing plays major role in defect predication. Software defect data includesredundancy, correlation, feature irrelevance and missing value. It is hard to ensure that the software is defectiveor non-defective. Software applications on day-to-day businesses activities and software attribute prediction suchaseffort estimation; maintainability, defects and quality classification are growing interest from both academic andindustry communities. Software defect predication can be done using several methods, in that randomforest andgradient boosting are effective. Even though they are efficient, the defect datasets contain incomplete or irrelevant features. The proposed system Average Probability Ensemble technique used to overcome those problems andgiveshigh classification result to compare another method, because it has integrated with three algorithms touseclassification performance. It gives more accurate results in publicly-available software datasets