This project is a real estate price prediction website that utilizes machine learning techniques to estimate property prices based on various factors. It includes a machine learning model built using scikit-learn and linear regression, using the Bangalore home prices dataset from Kaggle.com. The project also consists of a Python Flask server that serves HTTP requests and a website built using HTML, CSS, and JavaScript.
- Python
- Flask
- HTML
- CSS
- JavaScript
- scikit-learn
- Pandas
- NumPy
The project utilizes the Bangalore home prices dataset obtained from Kaggle.com. This dataset contains information about real estate properties in Bangalore, including features such as home square footage, number of bedrooms, location, etc. The dataset is used for training the machine learning model, enabling accurate price estimations based on property characteristics.
The machine learning model is built using scikit-learn and employs linear regression for price prediction. The model is trained on the Bangalore home prices dataset, and various data science concepts are applied during the model building process. These include data loading and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, and hyperparameter tuning using techniques like grid search cross-validation.
The project includes a web application that provides a user-friendly interface for predicting real estate prices. The web application is built using Flask, which serves as the backend server. Users can input property features such as home square footage, number of bedrooms, etc. through the website's interface. The Flask server then processes the user's input and returns the estimated price using the trained machine learning model. The website is designed using HTML, CSS, and JavaScript to create an interactive and visually appealing user experience.