Modelling software quality with GP

Document Type

Conference Proceeding

Publication Date



Computer Science


Software development managers use software quality prediction methods to determine to which modules expensive reliability techniques should be applied. This paper describes a genetic programming (GP) based system that classifies software modules as "faulty" or "not faulty", allowing the targetting of modules for reliability enhancement. The system is validated via a case study using software quality data from a very large industrial project. The demonstrated quality of the system is such that the system is being integrated into a commercial software quality management system.