Optainet-based technique for SVR feature selection and parameters optimization for software cost prediction

The software cost prediction is a crucial element for project’s success because it helps the project managers to efficiently estimate needed effort any project. There exist in literature many machine learning methods like decision trees, artificial neural networks (ANN), and support vector regressors (SVR), etc. However, studies confirm that accurate estimations greatly depend on hyperparameters optimization, proper input feature selection impacts highly accuracy of models (SCPM). In this paper, we propose an enhanced model using SVR Optainet algorithm. used at same time 1-selecting best set features 2-for tuning parameters model. experimental evaluation was conducted 30% holdout over seven datasets. performance suggested then compared tuned without selection. results were also Boruta random forest methods. experiments show overall datasets, Optainet-based method improves significantly outperforms