A new approach based on continuous genetic algorithm in software cost estimation
Farhad Soleimanian Gharehchopogh, Amir Pourali · 2015
Software Cost Estimation is a c onsiderable issue in the development and production of software projects. Delivery time of project and completing it in a timely fashion is a problem that software companies must be overcome them. Rec ently, the usages of Meta-heuristic tec hniques which are presented for software c ost estimation are increasingly growing. Prerequisite of relative acc urate estimation is work experienc e. Therefore, the risk associated with construction of projects is based on preliminary estimates. Increasing risk causes increasing unc ertainty about the initial program with increasing complexity and size of projec ts level of unc ertainty become higher. In this paper, we aim to develop an evolutionary model for software cost estimation by using continuous genetic algorithm. We sc rutinized adjusted COCOMO II model by using data set of NASA projec ts to examine the effect of the dev eloped model and showed the effec tiveness of the proposed algorithm in c orrection of parameters of COCOMO II. Experiment results show that this model offers very good estimate for software c ost estimation.