Software Effort And Function Points Estimation Models Based Radial Basis Function And Feedforward Artificial Neural Networks

Correct cost estimates is an essential element to develop economic proposals and being competitive in the market. Companies have to estimate the effort, time and cost before bidding for a project. An inaccurate estimate will lead to money and market share loss. To do that the expected software development size has to be estimated early in the development process. Many software models were presented in the literature to handle this task such as expert judgment, analogy-based estimation, formal estimation models and combination-based estimation models. These models were found to be risky and created many problems in practice related to availability of expertise and inaccurate estimate. Soft Computing techniques were successfully used to solve a diversity of problems in software engineering project cost estimation management. Earlier investigation proved that techniques such as Artificial Neural Networks (ANNs) can solve many problems in the field of software engineering project cost estimation management with promising results. In this paper, we propose two new models for software effort and function point estimation using ANNs. Two types of ANNs will be explored; the Feedforward (FF) and the Radial Basic Function (RBF) neural networks. The Albrecht data set with a number of attributes was used to provide our results. Developed results shows that ANNs models can provide an accurate estimate for both the software effort and number of function points.