Lung cancer remains the leading cause of cancer-related deaths worldwide, with early detection being crucial for improving patient survival rates. This research aims to enhance lung cancer diagnosis accuracy by applying advanced machine learning techniques. To address data imbalances, we implemented a comprehensive data preprocessing approach involving encoding, oversampling, and removal of duplicates. Utilizing a Kaggle dataset, we tested eight machine learning algorithms: Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN), LightGBM, Logistic Regression, Naive Bayes, Decision Tree, and AdaBoost. The SVM method achieved the best performance with an accuracy of 99.16%, precision of 99.17%, recall of 99.16%, and an F1 score of 99.16%. Our findings demonstrate the potential of SVM in enhancing lung cancer diagnostic tools, offering insights into optimizing machine learning models for medical applications. Future research will focus on improving model interpretability to facilitate practical clinical implementation.