Linear Regression Model for Agile Software Development Effort Estimation

Abstract

Software cost estimation is always an essential task for the development management as it requires for estimating the effort and the time required for developing the software. A project manager requires software estimation for making a decision and predict the total budget. Success or failure of software development depends on the accurate estimation of cost and time. There are numerous tools and techniques have been developed for estimating the software cost. But all these techniques are best suitable for the traditional development methodology. From the past two decades, the agile methodology has been com for software development. So the traditional cost estimation techniques may not give the appropriate results for agile development. In this paper, the multiple linear regression models are proposed for comparing the best model for agile development. The correlation between the dependent and independent variables are also found out. The results showed that the proposed model outperforms from the decision tree, stochastic gradient boosting, and random forest.