Car Price Prediction
Technologies Used
Python | Pandas | Seaborn | Matplotlib | sklearn | ExtraTreeRegressor | RandomForestRegressorDescription
Objective: The objective of this project is to predict the selling price of cars based on various input features using machine learning techniques. Input Features: 1. Manufactured year 2. Total km driven 3. Number of previous owners 4. Fuel type 5. Type of seller 6. Transmission type Data Preprocessing: • Cleaning Data: Handled missing values, outliers, and any inconsistencies in the dataset to ensure data quality. Machine Learning Model: • Algorithms Used: • Trained an ExtraTreesRegressor and RandomForestRegressor from the sklearn.ensemble module. • Hyperparameter Tuning: • Utilized RandomizedSearchCV to optimize hyperparameters for the RandomForestRegressor, enhancing model performance. Evaluation: • Evaluated the models’ performances using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²) to assess prediction accuracy. Results: • Achieved improved prediction accuracy of 97% through hyperparameter tuning and model comparison. • Highlighted insights from feature importance analysis, revealing crucial factors influencing car prices. Conclusion: • Summarizing the effectiveness of RandomForestRegressor with tuned parameters in predicting car prices based on the dataset. • Discussing potential enhancements or future directions, such as incorporating additional features or exploring different regression algorithms.