<![CDATA[Lung cancer is a condition where cells grow uncontrollably in the lungs due to carcinogens. Lung cancer is the first cause of death in men and women’s second cause of death. One way to reduce the death rate due to lung cancer is to carry out early detection, that is classification. The process of identifying and grouping objects with the same characteristics or characteristics into several predetermined classes is called classification. Several algorithms widely used in the classification process are Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). SVM has advantages, being able to identify hyperplanes separately to maximize the margin between two or more different classes, but it is difficult to use in large data, while KNN can perform large-scale data separation and is resilient to noise in the data. This study aims to build a model using the SVM and KNN algorithms to classify lung cancer. The lung cancer dataset has a total of 309 data, where data is divided using the percentage split method and k-fold cross validation on each algorithm used. The parameters used in evaluating the model are accuracy, precision, and recall. From the research, the highest accuracy, precision, and recall values were obtained in the SVM algorithm with the percentage split method with consecutive values, namely 95.16%, 88%, and 82.5%. This indicates that the SVM algorithm with the percentage split method performs better in classifying lung cancer than other algorithms and methods,]]>
