Improving software development effort estimation using support vector regression and feature selection

Abstract

Accurate and reliable software development effort estimation (SDEE) is one of the main concerns for project managers. Planning and scheduling a software project using an inaccurate estimate may cause severe risks to the software project under development such as delayed delivery, poor quality software, missing features. Therefore, an accurate prediction of the software effort plays an important role in the minimization of these risks that can lead to the project failure. Nowadays, the application of artificial intelligence techniques has grown dramatically for predicting software effort. The researchers found that these techniques are suitable tools for accurate prediction. In this study, an improved model is designed for estimating software effort using support vector regression (SVR) and two feature selection (FS) methods. Prior to building model step, a preprocessing stage is performed by random forest or Boruta feature selection methods to remove unimportant features. Next, the SVR model is tuned by a grid search approach. The performance of the models is then evaluated over eight wellknown datasets through 30%holdout validation method. To show the impact of feature selection on the accuracy of SVR models, the proposed model was compared with SVR model without feature selection. The results indicated that SVR with feature selection outperforms SVR without FS in terms of the three accuracy measures used in this empirical study.