Comparing Different Estimation Methods for Software Effort

Software project management begins with a set of collected activities called project planning activity. Before starting a project, the program’s team must evaluate the work to be done, the resources to be reorganized, and the time from the beginning computation. When these activities have been completed, the program’s team should establish a set of projects that will assign program engineering tasks, key milestones, determine the responsibly for each task, and identify associated dependencies among participants that may have a strong impact on progress. In general, there isn’t a complete accurate estimation method, but in this research I tried to discover the best programming methods to find the best programming estimate. The aim of this research is to present a study of the principles for reducing the cost of software and understanding how these techniques are applied to general program divisions. We provide basic algorithms in Artificial Intelligence, Artificial Neural Networks, Genetic Algorithms, and Fuzzy Logic Algorithm to determine which algorithm is the most appropriate to find the best estimates as possible in terms of precision. The best results were found in Neural Networks, but competitive results were found between types of Neural Networks (FFNN, CNN, ENN, RBFN and NARX). The NARX network was observed to provide the best accuracy, but Genetic Algorithm proved better than Fuzzy Logic which is the worst compared to Neural Networks and Genetic Algorithms.