Size-biased Hybrid Model for Software Defect Prediction

Overall software management generally includes software testing as an important aspect. Defect prediction in software is an important activity for testing a software. Hybrid models which include statistical and machine learning techniques have become very popular in recent days for predicting existence of errors in a software. Till recently software reliability models were developed based on the number of undetected bugs. However, some recent works on software reliability drastically changed the idea of estimating software reliability. The newly developed concept of "bug size" in a software is used in this article along with a proven hybrid method to predict software reliability. We have used this new method on several NASA data sets. Several standard criteria have been used to examine the efficacy of the proposed method and we obtained much better results compared to the earlier results on similar data sets.