Effort Estimation of Agile and Web-Based Software Using Artificial Neural Networks

Abstract

The agile methodology of software development is accepted as a superior alternative to conventional methods of software development, because of its inherent benefits like iterative development, rapid delivery and reduced risk. Hence, software developers are required to estimate the effort necessary to develop projects by agile methodology in an efficient manner because the requirements keep on changing. Web has become a part and parcel of our lives. People depend on Internet for almost everything these days. Many business units depend on Internet for communication with clients and for outsourcing load to other branches. In such a scenario, there is a necessity of efficient development of web-based software. For improving the efficiency of software development, resource utilization must be optimum. For achieving this, we need to be able to ascertain effectively, what kind of people/materials are required in what quantity, for development. This research aims at developing efficient effort estimation models for agile and web-based software by using various neural networks such as Feed-Forward Neural Network (FFNN), Radial Basis Function Neural Network (RBFN), Functional Link Artificial Neural Network (FLANN) and Probabilistic Neural Network (PNN) and provide a comparative assessment of their performance. The approach used for agile software effort estimation is the Story Point Approach and that for web-based software effort estimation is the IFPUG Function Point Approach.