Lung cancer is the most dangerous disease. Lung cancer has a huge impact on mortality rates worldwide. It is the top causes of cancer-related fatalities worldwide. Lung cancer development, prevention, and lifestyle are all linked. Smoking, occupational hazards, air pollution, an unbalanced diet, and other lifestyle factors are major contributors to lung cancer. The use of lifestyle indicators can aid in the early detection of lung cancer. In this study, a model is constructed based on lifestyle data to predict lung cancer, and the model is then extended to predict the level of lung cancer as low, medium, or high. The basic lifestyle parameters are examined first, and if the model forecasts the potential of lung cancer, the second component of the model analyses each parameter further and predicts the level of cancer. The first portion of the model employs logistic regression with k-fold validation and Support Vector Machine with k-fold cross-validation to predict lung cancer. The Support Vector Machine predicts with 90% accuracy, while the logistic regression model predicts with 92% accuracy. The second component of the model used SVM and Random Forest models to estimate the amount of malignancy, with Random Forest providing 96% accuracy and SVM providing 98.42% accuracy for cancer prediction. The goal of this study is to predict lung cancer early using data from lifestyle parameters.