The House Price Prediction System is designed to estimate housing prices based on various property and neighborhood features extracted from the Boston Housing dataset. Utilizing machine learning models, including Linear Regression, Decision Tree, and Random Forest with hyperparameter tuning, the system predicts housing prices and provides these predictions via a Flask-based web application. The Random Forest model achieved the highest accuracy with an R² score of 0.89 after tuning, establishing it as the optimal model for deployment. This report discusses the dataset, data preprocessing, exploratory data analysis, model training, evaluation, and the deployment process, along with a user-friendly HTML interface for real-time predictions. This system serves as a practical tool for users to estimate property values based on key characteristics.