🚗 Used Car Price Prediction

Welcome to the Used Car Price Prediction Challenge! 🎉 This project is designed to help you level up your end-to-end data science skills — from scraping real-world data, to building predictive models, to designing a user-friendly interface.

Each team will complete the entire workflow and compete to see who can engineer the best features and achieve the highest R² score.

📌 Project Overview

• Goal: Predict used car prices from dubizzle.com.om data.

• Teams: 4 teams of 5 members each.

• Focus: End-to-end ML pipeline + UI development.

• Key Skill Areas:

  • Data scraping & cleaning
  • Feature engineering
  • Regression modeling & evaluation
  • R² score optimization
  • Streamlit app development
  • Team collaboration & presentation

🛠 Workflow

1. Data Scraping & Cleaning

   • Scrape used car listings from dubizzle.com.om.
   • Handle challenges like missing data, text cleaning, and formatting.
   • Deliver a clean dataset ready for modeling.

2. Feature Engineering

   • Design and test new features to improve predictions.
   • This is the main differentiator between teams.

3. Model Development

   • Train at least 3 regression models (e.g., Linear Regression, Random Forest, XGBoost, Polynomial Regression).
   • Evaluate on a test split using R² score.
   • Select your best-performing model.

4. User Interface

   • Build a Streamlit app where users can input car details and get price predictions.
   • Focus on clarity, simplicity, and usability.

5. Presentation & Comparison

   • Share your process, challenges, and results.
   • Compete based on model accuracy, feature creativity, and app usability.

📊 Evaluation Criteria

Your project will be judged on:

1. Model Performance – R² score on test data.
2. Feature Engineering – originality, usefulness, and impact.
3. User Interface – usability, clarity, and design.
4. Collaboration & Presentation – documentation and delivery.

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/khoulaCode/Brain-Byte-Used-Car-Project
cd Brain-Byte-Used-Car-Project

2. Install Dependencies

pip install -r requirements.txt

3. Run the Streamlit App

streamlit run app.py

📂 Suggested Repository Structure

├── data/                # Raw and cleaned datasets  
├── notebooks/           # Jupyter notebooks for EDA and prototyping  
├── src/                 # Source code (scraping, modeling, utils)  
├── app/                 # Streamlit app files  
├── requirements.txt     # Project dependencies  
├── README.md            # Project documentation  
└── LICENSE  

🏆 The Challenge

All teams are solving the same problem. The key to winning is better feature engineering, smarter modeling, and a polished UI.