Exploring Machine Learning Approaches for Predicting Lung Cancer: A Comparative Study

Lung cancer is becoming more common, which emphasizes the significance of precise and user-friendly prediction methods for risk assessment and early identification. This research makes use of a dataset (284 cases and 16 attributes) that was acquired from the Online Lung Cancer Prediction System. The main goal is to find out how well machine learning techniques can predict the likelihood of lung cancer and give people useful information for making decisions. The collection contains a wide range of characteristics, such as lifestyle factors, health markers, and demographic data. To thoroughly assess predictive models, the study uses a variety of machine learning methods, including Logistic Regression, K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Decision Tree, Random Forest, XGBOOST, CATBOOST, LightGBM and Gradient Boosting. The study also investigates the effects of hyperparameter tuning, visualization strategies, and data preprocessing techniques on model performance. Keywords: Cancer prediction· Machine learning· Ensemble models