Software Bug prediction (SBP) helps in improving the quality of software to be developed. Bugs can be of different kinds such as functional, usability, security, etc, which leads to irrelevant features, data redundancy and missing samples. SBP is a very popular area in the IT world as thishelps in improving the software product.SBP is a complicated task that can be performed both manually (semi-automated) or automatically. The semiautomated task requires extensive knowledge about the product to be developed and manpower. On the other hand, automatic SBP eliminated such issues and improves the bug prediction cost significantly. In this paper, a multistage automatic SBP (ABPET) model using ensemble machine learning techniques is proposed. The proposed ABPET architecture is divided into three phases: in preprocessing stage the skewed and asymmetric data is preprocessed performed, in the second stage, ABPET classification model using ensemble ML algorithms RF and AdaBoost designed. Finally, a variety of estimated metrics such as precision, recall, accuracy F-measure, and Mathews co- relation coefficient are used to evaluate the constructed framework. The proposed multi-stage framework is tested on a publicly available dataset of the Promise repository. The experimental results indicated that AdaBoost outperforms the random forest by a 2% on accuracy and F- measure parameter.

software bug prediction, random forest, AdaBoost, ensemble learning, classification technique