A novel approach for optimization of effort estimation of agile projects using SVC_RBF along with neural network backpropagation

Abstract

In current scenario of software industry culture, an important and crucial task under project management is accurate estimation of effort which leads to successful project completion. A successfully completed project means that the project is developed within the planned budget and timeline which is mostly related to accurate effort estimation whereas inaccurate estimation of effort and cost results in failure of a project in context of delivery cost, time and other parameters. Most of the research has been proposed in the estimation of software projects using traditional frameworks. In recent years as there are technological advancements and there is a requirement of adaptation to technological changes, agile development methodology has attracted a lot of interest in research and development in software industries. The dynamic nature of agile requires development of various techniques which may be used for software cost and effort estimation. This paper deals with the study of few popular techniques and proposes a novel technique using ensemble of two techniques.

Subject Classification:

• 65K10

Keywords:

• Story points
• Velocity
• Scrum estimation
• SVR
• Backpropogation