Car-Dheko---Used-Car-Price-Prediction

Domain:

• Automotive Industry , Data Science, Machine Learning

Introduction:

• In this project, the task is to enhancing the customer experience and optimizing the pricing process for used cars by developing a machine learning model. This model, based on historical car price data, will take into account various features such as the car's make, model, year, fuel type, and transmission type. The goal is to predict the prices of used cars accurately and integrate this model into an interactive web application using Streamlit.

Skills take away From This Project:

• Data Cleaning and Preprocessing
• Exploratory Data Analysis
• Machine Learning Model Development
• Price Prediction Techniques
• Model Evaluation and Optimization
• Model Deployment
• Streamlit Application Development
• Documentation and Reporting

Results:

Random Forest:

• Achieved the best performance with the highest R² and the lowest MSE/MAE, making it the chosen model for deployment.
• Hyperparameter Tuning: Grid Search was employed to identify the optimal parameters, such as n_estimators and max_depth. By systematically testing a range of values for these parameters, Grid Search helped in determining the best combination that enhances the Random forest model's performance.

Streamlit Application Development:

• Deploying the predictive model through the Streamlit application revolutionizes the user experience at CarDekho by delivering swift and reliable price estimates for used cars.