Lung cancer has surpassed all other types of cancer as the most common cause of death worldwide. There is an increased mortality ratio and a poor diagnosis for lung cancer than any other types of cancer. Thus, forecasting rates becomes a difficult task for humans. Consequently, numerous machine learning algorithms have been suggested to offer efficient and speedy forecasting of ambiguous raw data with minimal inaccuracies. In this research, various machine learning algorithms including Support Vector Machine, Adaptive Boosting, k-Nearest Neighbor, Logistic Regression, J48, and Naïve Bayes have been implemented on medical history and physical activities of participants to identify and classify the lung cancer. Various physiological factors have been taken into account and applied to machine learning algorithms. The results indicate that all algorithms can predict incidence rates with high scores; however, Logistic Regression achieved better performance with an accuracy and f-measure of 94.7% compared to other algorithms.