Portfolio

NBA

Developed with Python utilizing the TensorFlow library, the model is trained on over 19,000 games from the past 2 decades. The purpose of the project is to analyze and predict game outcomes, giving valuable insights to sports organizations and teams. The model is integrated with a Django web app, which provides prediction statistics, graphs, and today's games, displayed in a responsive and intuitive user interface.

SquashBug

SquashBug is a web-based ticket management system that follows MVC architectural standards and is built using the Django framework. The user interface is designed using Bootstrap, CSS, and HTML, providing a clean and intuitive layout. The main feature is a dashboard that gives a clear overview of recent tickets, allowing users to easily search, sort, and paginate through the data. Each ticket is displayed with relevant information such as severity, date, and author. The dashboard also includes interactive graphs that provide valuable insights into the ticket data.

TotallySocial

Developed with React for the front-end and Django for the back-end, the platform offers a dynamic feed of user-generated posts, enabling anyone in the world to easily engage with the latest trends. Overall, the project showcases my ability to design and develop a user-friendly and interactive social media platform that can drive engagement and foster connections.

Classifier

The model is trained on over 60,000 examples from the MNIST dataset and is able to accurately classify handwritten numbers. I implemented this project using the PyTorch framework and optimized the model's performance through techniques such as data augmentation and regularization. This project showcases my ability to use cutting-edge machine learning techniques and tools, as well as my understanding of neural network architecture and training.