Software defects prediction using operating characteristic curves

Abstract

We present a software defect prediction model using operating characteristic curves. The main idea behind our proposed technique is to use geometric insight in helping construct an efficient and fast prediction method to accurately predict the cumulative number of failures at any given stage during the software development process. Our predicfive approach uses the number of detected faults instead of the software failure-occurrence time in the testing phase. Experimental results illustrate the effectiveness and the much improved performance of the proposed method in comparison with the Bayesian prediction approaches. © 2007 IEEE.