COMPARISION OF MAINTENANCE ACTIVITY FOR EFFORT ESTIMATION IN OPEN SOURCE SOFTWARE PROJECTS
Avneet Kaur · International Journal of Advanced Research in Computer Science · 2017
Software estimation accuracy is amongst the biggest challenges for software developers. The most significant activity in software project management is Software development effort prediction. Many models have been proposed to make software effort estimations, but still no single model can predict the effort accurately. The demand for accurate effort estimation in the software industry is still a challenge. Accurate, precise and reliable estimates of effort at early stages of project development hold great importance for the management to meet the competitive demands of today's world. Software cost estimation is one of the most crucial tasks and predicts the effort and development time needed to develop a software system. It helps the software industries to manage their software development process efficiently. In this paper, we introduce an approach to building an effort estimation model for Open Source Software. For this purpose, effort data is mined from the developer's bug fix activities history. Our approach determines the actual time spend to fix a bug and considers it as an estimated effort. We propose an artificial neural-network-based approach to predict the amount of effort and development time of developers required for bug resolution. This paper investigates the use of Back-Propagation Neural networks for software effort estimation. The primary purpose of this paper is to estimate the software development effort using Artificial Neural-Network based techniques to improve accuracy of developers for bug resolution.