Software cost estimation is one of important activity of software development. Software cost estimation plays an important role in software engineering practice, often determining the success or failure of contract negotiation and project execution. Cost estimation’s deliverables such as effort, schedule, and staff requirements are valuable information for project formation and execution. Genetic Algorithm can offer some significant improvements in accuracy and has the potential to be a valid additional tool for software effort estimation. It is a non-parametric method since it does not make any assumption about the distribution of the data and derives equations according only to the fitted values. In this study, applicability and capability of Genetic Algorithm techniques for application in software cost estimation as a predictive tool has been investigated. It is seen that GA models are very robust, characterised by fast computation, capable of handling the noisy and approximate data that are typical of data used here for the present study. From the analysis of the results given earlier it is seen that GA has been able to perform well for the prediction of effort estimation. Due to the presence of non-linearity in the data, it is an efficient quantitative tool. The studies has been carried out using MATLAB simulation environment.