This project tackles the global health crisis of cardiovascular diseases through data-driven predictive analytics. With the data set sourced from kaggle, our initiative aims to classify heart disease using diverse numerical and categorical features. The process involves meticulous data exploration, scaling, and feature selection. Recognizing potential issues like over fitting, we propose advanced techniques such as XGBoost and ensemble methods for model refinement. The project evaluates various classification algorithms and employs iterative strategies for optimal predictive accuracy.

The flow of methodology used in the project is 1) meticulously pre process data, 2) emphasize feature scaling and selection. 3)Exploratory data analysis which guides the extraction of vital insights, laying the foundation for modeling. 4)Address over fitting, we introduce advanced techniques like XGBoost and ensemble methods to ensures optimal model performance. The project integrates diverse classification algorithms, enabling a comprehensive evaluation. This project offers a detailed glimpse into our systematic methodology, emphasizing its iterative nature and commitment to enhance predictive accuracy in cardiovascular disease detection.