<![CDATA[Software development cost estimation remains a major challenge in project management because the complexity of software projects and the uncertainty of cost-influencing factors often lead to inaccurate estimates, adversely affecting resource allocation, budgeting, and project planning. This study aims to develop and evaluate an XGBoost-based software development cost prediction model optimized through Optuna-based hyperparameter optimization, as well as to investigate whether hyperparameter optimization can significantly improve prediction accuracy compared with the default XGBoost configuration. The proposed approach was evaluated using the Constructive Cost Model (COCOMO) dataset, a widely used benchmark for software cost estimation. The methodology consists of data preprocessing, XGBoost model training, Optuna-based hyperparameter optimization, and model evaluation using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Magnitude of Relative Error (MMRE), and the coefficient of determination (R²). Experimental results show that the optimized XGBoost model significantly outperformed the default configuration. The default model achieved an MAE of 189.6093, an RMSE of 296.1262, an MMRE of 132.42%, and an R² of 0.7162, whereas the optimized model reduced the MAE to 101.4871, RMSE to 134.7717, and MMRE to 34.04%, while increasing the R² to 0.9412. These results demonstrate that Optuna-based hyperparameter optimization substantially enhances the predictive performance of XGBoost for software cost estimation. The proposed approach provides a reliable decision-support tool for software project managers, enabling more accurate cost estimation, improved resource planning, and more effective project management.]]>
Copyrights © 2026
