Software development time estimation based on a new Neuro-fuzzy approach

Two of the three most important causes of Information Technology projects failure have been related to a poor resource estimation. In average, software developers expend from 30% to 40% more effort than is estimated. Because that no single technique to estimate software development effort is best for all situations, it is important to propose new models to compare their results and then generate more realistic estimates. In this study, the aimed is to present a hybrid model that combine fuzzy logic and neural networks for achieving higher accuracy for estimating the development time of software projects. The accuracy of time estimation for a Neuro-Fuzzy System (NFS) is statistically better than the accuracy obtained from a previous NFS and statistical regression (model most used by default to compare) when the forty-one modules developed from ten programs were used as dataset. Results show that the value of MMRE (Mean of Magnitude of Relative Error) applying a NFS was substantially lower than MMRE applying a previous NFS and statistical regression. It can be conclude that a new NFS could be applied for estimating the effort of software development projects when they have been individually developed on a disciplined process.