Incorporating qualitative and quantitative factors for software defect prediction

  • Authors:

  • Dandan Wang;Qing Wang;Zhenghua Hong;Xichang Chen;Liwen Zhang;Ye Yang

  • Affiliations:

  • Laboratory for Internet Software Technologies, Institute of Software, Beijing, China;Laboratory for Internet Software Technologies, Institute of Software, Beijing, China;Chinese Development Bank, Beijing, China;Chinese Development Bank, Beijing, China;Chinese Development Bank, Beijing, China;Laboratory for Internet Software Technologies, Institute of Software, Beijing, CA, China

  • Venue:
  • Proceedings of the 2nd international workshop on Evidential assessment of software technologies
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Defect is an important quality attribute of software. Defect is injected in development process and depended on the maturity level of the processes. How many defects were detected is enough? In any software organization, effort estimation and defect prediction are big challenges. Predicting the number of defects in the early stage of software development life cycle will be more helpful for the organizations to estimate the quality of developed product and optimize the resources schedule. Especially in outsourcing organization, the early precise defect prediction can help them to monitor the supplier's process and establish the criteria to verify the outsourcing products. Chinese development bank (CDB) is such an outsourcing organization, who applied SAM process area of CMMI to manage their outsourcing projects. In this paper, we proposed a prediction mode, which incorporated the qualitative factors from COQUALMO and the quantitative data collected from 21 historic financial projects of CDB. Principal Component Analysis (PCA) method was adopted to analyze the inter-correlated factors, and the key factors were determined to simplify the proposed model. We also evaluated its performance and compared with the software defect introduction (DI) model of COQUALMO. The results show that 66.67% predicted results are better than DI model and 80.5% predicted results have AE which are less than 50 while 95.24% predicted results have AE which are less than 100.