Hackathon Project: OlympiPredict

Quick Update: Won 2nd Place for Best Paris 2024 Olympics Category!!

Team Members

• Faiz Mustansar: Lead
• Fawaz Rizwan: Developer
• Talha Naveed: Developer

Project Overview

Our hackathon project aims to predict the medal winners of the 2024 Paris Olympics by analyzing data from the 2021 Tokyo Olympics and other relevant datasets. We utilize machine learning techniques and data analysis to make informed predictions about the performance of various countries in the upcoming games.

Project Structure

1. Data Collection

• Datasets:
  • Tokyo 2021 Olympics medal tally
  • Athlete statistics (age, gender, previous performances)
  • Historical Olympic performance data (2021)
• Sources:
  • Olympic Official Website
  • Sports Reference
  • Kaggle Datasets

2. Data Preparation

• Cleaning: Handle missing values, remove duplicates, and correct inaccuracies.
• Feature Engineering: Create new features such as medal weight, total teams, and top winners for each sports

3. Data Analysis and Visualization

• Tools: Python, Pandas and R Programming

4. 2024 Predictions

• Method: Use 2021 sports-specific top teams and participating countries data and Apply algorithms to predict 2024 results based on performance and other factors.

Future Improvements**

• Efficiency: Develop methods to efficiently gather data on participating teams.
• Algorithm Enhancement: Enhance prediction algorithms with more robust datasets.
• Responsiveness: Improve the responsiveness

Installation

1. Clone the repository:

   git clone https://github.com/faizm10/CodeDexHackathon
   cd CodeDexHackathon

2. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install the required packages:

   pip install -r requirements.txt

Contribution Guidelines

git checkout -b {your-name/feature}
git add .
git commit -m "New Feature"
git push --set-upstream origin '{your-name/feature}'
git checkout main
git pull #after PR gets merged into main branch

License

This project is licensed under the MIT License. See the LICENSE file for details.