Feature Subset Selection in Software Cost Models using the Artificial Immune Algorithm

Tad Gonsalves and Yu Aiso


Feature Subset Selection, meta-heuristics, Artificial Immune System


Software development projects are notorious for being completed behind schedule and over budget and for often failing to meet user requirements. A variety of cost estimation models have been proposed to predict development costs early in the lifecycle with the hope of managing the project well within time and budget. However, studies have reported rather high error rates of prediction even in the case of the well-established and widely acknowledged models. This study focuses on the improvement and fine-tuning of the COCOMO 81 and the Desharnais model through Feature Subset Selection, using the Artificial Immune System. Our research reconfirms the conventional data mining techniques and makes further improvement in the prediction accuracy. The AIS meta-heuristic approach is domain-independent and faster compared to the wrapper data mining method which is slow and heavily dependent on the domain experts’ heuristics.

Important Links:

Go Back