04 Improved Fault-Prone Detection Analysis of Software.pdfVIP

      Vol. 9, No. 4, pp. 421-433, 2012 QTQM ? ICAQM 2012 Experience in Predicting Fault-Prone Software Modules Using Complexity Metrics Liguo Yu1 and Alok Mishra2 1Computer Science and Informatics, Indiana University South Bend, IN, USA 2Department of Computer Software Engineering, Atilim University, Ankara, Turkey (Received November 2011, accepted May 2012) ______________________________________________________________________ Abstract: Complexity metrics have been intensively studied in predicting fault-prone software modules. However, little work is done in studying how to effectively use the complexity metrics and the prediction models under realistic conditions. In this paper, we present a study showing how to utilize the prediction models generated from existing projects to improve the fault detection on other projects. The binary logistic regression method is used in studying publicly available data of five commercial products. Our study shows (1) models generated using more datasets can improve the prediction accuracy but not the recall rate; (2) lowering the cut-off value can improve the recall rate, but the number of false positives will be increased, which will result in higher maintenance effort. We further suggest that in order to improve model prediction efficiency, the selection of source datasets and the determination of cut-off values should be based on specific properties of a project. So far, there are no general rules that have been found and reported to follow. Keywords: Binary logistic regression, complexity metrics, fault-prone software module. ______________________________________________________________________ 1. Introduction oftware quality analysis and prediction focuses on detecting high-risk fault prone program modules, allowing practitioners to allocate project resources strategically [9, 34].Through allocating more testing resources on fault-prone modules, we can