Author
M.Sc. of Information Systems, Software Engineering, the Arab Academy for Science, Technology and Maritime Transport, Egypt
Abstract
Recently, early prediction of software defects using machine learning techniques has attracted more attention from researchers due to its importance in producing successful software. On the other side, it reduces the cost of software development and facilitates procedures to identify the reasons for determining the percentage of defect-prone software in the future. There is no conclusive evidence for specific types of machine learning that will be more efficient and accurate in predicting software defects. However, some of the previous related work proposes ensemble learning techniques as a more accurate alternative. This paper introduces the resample technique with three types of ensemble learners; Boosting, Bagging, and Rotation Forest, using eight base learners tested on seven types of benchmark datasets provided in the PROMISE repository. Results indicate that accuracy has been improved using ensemble techniques more than single leaners especially in conjunction with Rotation Forest with the resampling technique in most of the algorithms used in the experimental results.