This study explores the prediction of human facial beauty levels using machine learning models combined with Golden Ratio principles. A dataset of 500 celebrities sourced from the internet, was analyzed using facial landmark detection techniques to compute Golden Ratio (ϕ) based features. The models were evaluated using accuracy, precision, recall, and F1 score to assess classification performances. The Random Forest model outperformed the Decision Tree, achieving higher accuracy as 92.08% over 89.68%. The confusion matrix confirmed that the Random Forest model performed well across all categories. These findings highlight that integrating facial landmark analysis with machine learning enhances automated beauty assessment and underscores the robustness of the Random Forest model in achieving higher accuracy and a balanced trade-off between precision and recall.