Our goal with this competition is for college students to be able to test their forecasting and data science skills while gaining valuable experience in a sports analytics context. We also want to improve on the existing bracket challenge model to incentivize accurate predictions rather than more of a game theory approach.

You will be forecasting the outcomes of the men's 2024 collegiate basketball tournament by submitting a CSV with the win percentages of every possible matchup in the tournament. Because there are 2016 possible matchups (after removing teams that lose in the first four, your submission CSV should have at least 2016 rows (you may include all First Four teams if you wish, but you will not be graded on First Four matchups). 
Each row should have a Team 1 column, a Team 2 column, and a Win Percentage column denoting the expected win percentage for Team 1 if these two teams played.

Because the first matchup of the tournament is March 21st, you have until then to make your submission. We will provide data to help you, but you may use any outside sources you wish for training and inference. Selection Sunday is March 17th, so of course you will not be able to generate your inferences until that date, but you should be able to train you model as early as you wish.

Two important notes: 

- This competition is open only to College Students.

- The TOP 3 TEAMS WILL ALL RECEIVE SMT MERCH AND SWAG FOR WINNING!

Good luck to everyone and Go Duke!