ABSTRACT Software metric and estimation is base on measuring of software attributes which are typically related to the product, the process and the resources of software development. One of the greatest challenges for software developers is predicting the development effort for a software system based on some metrics for the last decades. Project managers are required to the ability to give a good estimation on software development effort. Most of the traditional techniques such as function points, regression models, COCOMO, etc, require a long-term estimation process. One of the new approaches that called soft computing techniques may offer an alternative for this challenge. This paper described an enhanced soft computing model for the estimation of software cost and time estimation. Result shows that the value of MMRE (Mean of Magnitude of Relative Error) applying soft computing was substantially lower than MMRE applying by algorithmic models.
