Welcome to the Boston House Price ML Predictor! This project uses Machine Learning to predict house prices in the Boston area based on various features.
This application utilizes a Support Vector Regressor (SVR) model trained on a dataset of Boston housing data to provide you with estimated house prices based on specific features.
- The Support Vector Regression (SVR) model was chosen for this project due to its ability to handle both linear and non-linear relationships in the data, making it suitable for predicting house prices, which often exhibit complex patterns. SVR is also effective in handling high-dimensional datasets and has been widely used in real estate prediction tasks, making it a robust choice for accurate price forecasting.
- Visit the Boston House Price ML Predictor web application.
- Enter the values for the following features:
- Crime Rate (CRIM)
- Proportion of Residential Land Zoned (ZN)
- Proportion of Non-Retail Business Acres (INDUS)
- Charles River Dummy (CHAS)
- Nitric Oxides Concentration (NOX)
- Average Number of Rooms (RM)
- Proportion of Owner-Occupied Units Built Before 1940 (AGE)
- Weighted Distances to Employment Centers (DIS)
- Click the "Predict" button to get an estimated house price.
To run this application locally, you'll need to have Python and the required libraries installed. You can find a list of dependencies in the requirements.txt file.
- Clone this repository:
git clone https://github.com/Yarlagadda-saimanoj/Boston-House-Price-ML-Predictor.git - Install the required dependencies:
pip install -r requirements.txt - Run the app:
streamlit run app.py
- Languages:
- Libraries:
This code is distributed under the terms of the MIT License.