Building data-driven solutions to real-world problems.

Who we are

Cornell Data Science (CDS) is an undergraduate project team dedicated to building data-driven solutions to a variety of real-world challenges. Our work combines data science techniques, such as machine learning, deep learning, and data visualization, with system design, data infrastructure, and financial analytics to tackle meaningful problems.

Our mission

We aim to drive innovation and excellence in data science through our four specialized subteams and a wide range of hands-on projects. Each project emphasizes collaboration, innovation, and translating theoretical knowledge into practical impact.

Meet the subteams

Data Engineering

Our projects operate at the cutting-edge intersection of theory and practical application across multiple disciplines. They provide an educational platform for our members to apply their data science knowledge while building solutions that address real pain points in the broader Cornell community.

F1ML2

Pushing the limits of data-driven forecasting in Formula 1 racing, enhancing our previous model by implementing ensemble methods and improving portfolio simulations.

LiveDance

Creating a computer vision-powered dance coach that watches your moves, spots your mistakes, and teaches you how to perfect every step.

CDS Compute Cluster

Building a shared compute cluster to give CDS members on-demand access to local GPUs and job scheduling without the cloud cost.

GitDistributed

Rebuilding Git from the ground up to master the challenges of distributed systems, networking, and version control.

RL Proof Generator

Developing a reinforcement learning-powered assistant to verify, guide, and even generate formal mathematical proofs.

Community initiative

Beyond projects, we are also committed to community education. Every semester, we offer INFO 1998: Introduction to Machine Learning, a hands-on introductory course that equips students with practical skills to build their first machine learning models using real-world datasets.

Support us

Your gift directly funds:

• Project infrastructure and computing resources
• Student development and mentorship
• Community education through INFO 1998

With your help, we can continue building data-driven solutions that make an impact on our members, the Cornell community, and beyond!

Follow our journey on Instagram: https://www.instagram.com/cornelldatascience/

As a registered student organization, we are committed to equal access to all of our programs and do not discriminate based on any protected identity status.