Our project aims to identify key risk factors for Coronary Artery Disease (CAD) using machine learning models and the UK Biobank dataset. By analyzing a comprehensive set of patient data, we seek to uncover novel insights into the complex interplay of factors contributing to CAD development. Our methodology involves dataset exploration, feature selection, data cleaning, model selection, hyperparameter tuning, and result analysis. Through this process, we aim to develop a predictive tool with high accuracy in CAD risk assessment. The project's outcomes will contribute to advancing personalized medicine and public health strategies, ultimately improving CAD prevention and treatment approaches.