Story Point Approach based Agile Software Effort Estimation using Various SVR Kernel Methods

Abstract

Agile software development process represents a major departure from traditional, plan-based approaches to software engineering. Estimating effort of agile software accurately in early stage of software development life cycle is a major challenge in the software industry. For improving the estimation accuracy, various optimization techniques are used. The Support Vector Regression (SVR) is one of these techniques that helps in getting optimal estimated values. The main objective of the research work carried out in this paper is to estimate the effort of agile softwares using story point approach. An attempt has been made to optimize the results obtained from story point approach using various SVR kernel methods to achieve better prediction accuracy. A performance comparison of the models obtained using various SVR kernel methods is also presented in order to highlight performance achieved by each method.