Used Car Price Prediction with Machine Learning (Regression) and Streamlit App:

🔗 PROJECT LINKS

• 💻 Used Car Price Prediction Streamlit App - Interact with the model in real-time.
• 💻 Notebook -Explore the project

Note

• If the app is asleep, click "Yes, get this app back up!", and it will wake up within a few seconds.

• In case the files cannot be viewed directly on GitHub, please download the files and open them in their respective applications for proper access.

Introduction

In this project, I aim to build a predictive model that estimates the selling price of used cars based on various features. This analysis involves constructing a machine learning model and conducting a thorough exploratory data analysis (EDA) to uncover insights and patterns within the data.

Goal

The primary goal is to assist potential buyers and sellers in making informed decisions by predicting car prices based on historical data. This model can help in pricing used cars more effectively, ultimately benefiting both consumers and dealers.

Key Highlights

• Built a model using Linear Regression, Decision Tree, Random Forest, and XGBoost, improving the score from -2.51e+26 to approximately 75% accuracy with XGBoost.
• Conducted EDA and feature engineering for model building, with insights documented in the notebook.
• Performed hyperparameter tuning using RandomizedSearchCV to optimize model performance.
• Developed a basic Streamlit app for real-time price predictions.