Tuning of COCOMO II Model Parameters for Estimating Software Development Effort using GA for PROMISE Project Data Set

Abstract

In this paper, we have tuned the parameters of COCOMO II model to estimate the software development effort using genetic algorithm (GA). Results obtained by applying GA are have been compared with results obtained by applying particle swarm optimization (PSO) published in previous paper. COCOMO II model is modified by introducing some more parameters to predict the software development effort more precisely. The performance of this parametric model is tested on the past PROMISE and NASA projects data set