Heart Disease Prediction

Data preprocessing & cleaning – making the dataset ready for analysis

Dimensionality reduction with PCA – simplifying data while keeping critical information

Feature selection – identifying the most important predictors for heart disease

Supervised learning models – building and testing classification models

Unsupervised learning techniques – exploring patterns and hidden structures in the data

Hyperparameter tuning – fine-tuning models for better accuracy

Interactive UI with Streamlit – creating a user-friendly interface to interact with predictions

Deployment – taking the model from local development to a live environment