Lung cancer persists as the preeminent cause of cancer-related mortality globally, underscoring the imperative for refined early detection strategies to ameliorate patient prognosis. This investigation advances diagnostic precision through sophisticated machine learning paradigms. To address dataset discrepancies, a rigorous preparation framework was implemented, including Chi-square-based selection of the top ten features, encoding, oversampling, and hyperparameter tuning. Eight algorithms Naive Bayes, Decision Tree, Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors, and Logistic Regression underwent rigorous assessment using the Kaggle dataset. The SVM demonstrated excellent performance, producing an accuracy of 97.78%, precision of 97.87%, recall of 97.78%, and F1-score of 97.78%, confirming its supremacy in predictive modeling for lung cancer diagnosis.