Abstract: Software cost estimation is one of the most challenging issues in software project management. To produce the accurate estimation, many models have been developed, but no model has efficient with the uncertainty of the project development. Most of these models are based on the size measure, such as Lines of Code (LOC) and Function Point (FP). Size estimation accuracy directly effect on cost estimation accuracy. The COCOMO model is the most important model for Software Cost Estimation. Today’s effort estimation models are based on soft computing techniques as, genetic algorithm, the fuzzy logic, neural network etc for finding the accurate predictive software development effort and time estimation. The aim of this paper is to optimize the parameters of COCOMO Model with genetic algorithms.

Keywords: Software cost estimation, COCOMO model, genetic algorithm, Variance Account