Effort Estimation of Software products by using UML Sequence models with Regression Analysis

Software product development is an indispensible part of the society we live in. In order to produce quality products economically, efficiently and within targeted completion date, estimation for development needs to be fairly precise. This work comes up with quite a viable estimation of the development efforts for the current day web applications. The modus operandi in this work collects facts existing in the Unified Modeling Language Sequence models generated for Object based systems. These facts, in combination with customized regression analysis programs specifically written for this work were used for the required estimation. To be specific: Decision Tree, Support Vector, Extreme Gradient Boosting and Bayesian Ridge Regression methods were used to estimate the efforts. The outcomes obtained by these methodologies, established its preciseness. As per the observations from experiments conducted, it was quite evident that the Bayesian Ridge Regression is providing the best accuracy compared to other Machine Learning models.