PREDICTING SOFTWARE DEVELOPMENT EFFORT USING ARTIFICIAL NEURAL NETWORK
Yogesh Pal Singh, Arvinder Kaur, Pradeep Kumar Bhatia, Om Prakash Sangwan · International Journal of Software Engineering and Knowledge Engineering · 2010
Software effort estimation is an important and integral part of software development life cycle of any project. However, cost, time and manpower estimation is required prior to implementation of the project. The objective of this work is to explore the possibilities of application of Artificial Neural Network (ANN) as a tool for predicting software development effort. We proposed an ANN model for predicting software development effort. A multilayer feed forward network is trained using back-propogation algorithm and demonstrated to be suitable. This study used the training and validation data, which is randomly selected from the data repository of 650 projects [8]. The experimental results indicate that the Mean Absolute Relative Error (MARE) is 0.261 of ANN model and shows that ANN model is a competitive model for predicting software development effort.