Common threats to software quality predictive modeling studies using search-based techniques

Abstract

Development of Software Quality Predictive Models (SQPM) is an important research area as it helps in effective use of project resources and assures a good quality software product. A number of studies in literature have developed successful SQPM using search-based techniques which are meta-heuristic in nature. However, in order to perform a successful empirical study which develops SQPM using search-based techniques, it is essential to consider various probable sources of threats to the empirical study so that the developed models are realistic and efficient. This study reviews and analyzes 33 empirical studies in literature which have successfully used search-based techniques for prediction of two common software quality attributes i.e. fault-proneness and change-proneness in order to comprehensively present various probable threats to such studies. The study also proposes remedial actions to mitigate these threats and presents an analysis of the most common threats which are missed by researchers.