Skip to content

Winning projects

What strong projects actually look like — the question they asked, the design that survived review, and the one decision that made the difference.

Archive entries are summaries compiled for study. Read them for how a project was structured, argued, and defended — not as a template to reproduce. Copying someone else's project is the one thing that will end yours.

1 project

advanced

A Novel Second-Order Cone Programming Algorithm

Michelle Wei

First place · Regeneron ISEF 2024

A faster algorithm for second-order cone programming, a convex optimisation form that sits underneath applications in machine learning, transportation and financial systems.

  • optimization
  • convex-programming
  • algorithms
  • +1