House Price Prediction Application for the Philippines

This application provides an estimated house price for properties in the Philippines based on various features like the number of bathrooms, bedrooms, car spaces, floor area, land size, and total rooms. It leverages a machine learning model to provide these estimations.

Prediction Algorithm: This predictor uses a Random Forest Regressor model. Random Forests are ensemble learning methods that operate by constructing a multitude of decision trees during training and outputting the mean prediction (regression) of the individual trees. This approach helps to improve accuracy and control over-fitting.

Backend: Flask (Python) - Used for serving the web application and hosting the machine learning model API.

The machine learning model was trained on a dataset of house prices from the Philippines. You can find the exact dataset used for training on Kaggle:

The implementation and methodology for this project were guided by principles often found in machine learning regression tasks. For a general understanding of Random Forest Regression and its application, you can refer to resources such as: