A Comparative Analysis of Regression Models for Software Effort Estimation

Abstract

Software Effort Estimation is the utmost task in software engineering and project management. This is important to estimate cost properly and the number of people required for a project to be developed. Many techniques have been used to estimate cost, time, schedule and required manpower for software development industries. Nowadays software is developed in a more complex way and its success depends on efficient estimation techniques. In this research, we have compared five regression algorithms on different projects to estimate software effort. The main advantage of these models is they can be used in the early stages of the software life cycle and that can be helpful to project managers to conduct effort estimation efficiently before starting the project. It avoids project overestimation and late delivery. Software size, productivity, complexity and requirement stability are the input vectors for these regression models. The estimated efforts have been calculated using Ridge Regression, Lasso Regression, Elastic Net, Random Forest and Support Vector Regression. We have compared unitedly these models for the first time as software effort estimators. R-squared Score, Mean Squared Error (MSE) and Mean Absolute Error (MAE) are calculated for these regression models. Ridge, Lasso and Elastic Net show comparatively better results among others.