Research on Sailboat Sales Pricing Models Based on Random Forest and XGBoost Algorithms

As global trade grows, the increasing demand for sailboats, influenced by factors like manufacturing costs and economic conditions, highlights the need for accurate price predictions in a fluctuating market. This study leverages Random Forest and XGBoost machine learning models to predict sailboat pricing by analyzing a dataset collected from various economic sources. A robust data cleaning process was employed, followed by data normalization and dimensionality reduction through Principal Component Analysis. The models were optimized and evaluated using cross-validation techniques, with a focus on understanding feature importance through sensitivity analysis. The performance was quantified using metrics such as MSE, RMSE, and R². Ultimately, the XGBoost model outperformed Random Forest, providing a more accurate and reliable prediction of sailboat prices, attributed to its ability to handle complex variable interactions more effectively.