Quality prediction modelling for software customisation in the absence of defect data

Abstract

Given the rapid development of computer techniques and the growing demand from the customer side, system customisation is becoming a necessity for software development, and this area of specialisation is attracting increasing attention from scholars. The innovative functions or applications brought by customisation are challenging the traditional software quality prediction approaches, many of which rest on the premise that the defect data from current system testing or similar systems should be available. This paper proposes a software quality prediction model which focuses on software quality prediction when defect data is unavailable. In addition, this paper improves a quality prediction model presented through substituting the traditional clustering algorithm with a less noise-sensitive algorithm. Through an empirical study on a real ERP system under customisation, the paper concludes that the quality prediction model is feasible in practice and the improved model performs better than the original one in prediction accuracy and effectiveness.