v-SVR Polynomial Kernel for Predicting the Defect Density in New Software Projects

TL;DR

This paper explores using v-SVR with a polynomial kernel to accurately predict defect density in new software projects, outperforming simple linear regression especially for mainframe and third-generation language projects.

Contribution

It introduces the application of v-SVR with a polynomial kernel for defect density prediction, demonstrating its superiority over traditional regression methods.

Findings

v-SVR with polynomial kernel outperforms SLR in certain project types

Statistical tests confirm significance of v-SVR's improved accuracy

Effective for mainframe and third-generation language projects

Abstract

An important product measure to determine the effectiveness of software processes is the defect density (DD). In this study, we propose the application of support vector regression (SVR) to predict the DD of new software projects obtained from the International Software Benchmarking Standards Group (ISBSG) Release 2018 data set. Two types of SVR (e-SVR and v-SVR) were applied to train and test these projects. Each SVR used four types of kernels. The prediction accuracy of each SVR was compared to that of a statistical regression (i.e., a simple linear regression, SLR). Statistical significance test showed that v-SVR with polynomial kernel was better than that of SLR when new software projects were developed on mainframes and coded in programming languages of third generation