This project utilizes machine learning techniques, specifically linear regression, to predict the price of used cars based on various features such as the car's make, model, year, kilometers driven, and fuel type. Implemented using Streamlit, a user-friendly interface library, users can input details of a car, and the model predicts the approximate price based on historical data. This project serves as a practical tool for individuals interested in estimating the value of used cars before making a purchase or for sellers seeking to set competitive prices in the market.
- Machine learning model trained on historical used car data.
- Streamlit interface for easy interaction and prediction.
- Input fields for car details such as make, model, year, kilometers driven, and fuel type.
- Predicts the approximate price of the used car based on user inputs.
- Python
- Scikit-learn (for machine learning)
- Streamlit (for user interface)
- Pandas (for data manipulation)
- NumPy (for numerical computations)
- Pickle (contains trained model)
- Jupyter notebook