|International Journal of Computer Applications
|Foundation of Computer Science (FCS), NY, USA
|Volume 177 - Number 1
|Year of Publication: 2017
|Authors: Lujain A. Hussein, Kulood A. Nassar, Maysaa A. Naser
Lujain A. Hussein, Kulood A. Nassar, Maysaa A. Naser . Recurrent Neural Network based Prediction of Software Effort. International Journal of Computer Applications. 177, 1 ( Nov 2017), 40-46. DOI=10.5120/ijca2017915664
The enormous efforts of software systems and unexpected efforts in the late phases of software development in software engineering field led to using methods to estimate software effort at early stages of software preparing phases. Therefore, the question remains how can develop an estimation method to be more accurate and gives a prediction for future software efforts. This paper presents a proposed method for software effort prediction, to enhance software effort estimation phase. The proposed method utilizes feed-forward neural network in recurrent fashion to make a prediction and adapt to handle with varying software types in software engineering. The proposed method (RFFNN) used to enhance the results of ordinary software effort estimation methods, RFFNN gives more efficient results by making a prediction for future software efforts.