Duke Sports Analytics Club and SMT (SportsMEDIA Technology) are hosting a 2024 March Madness modeling competition, in which participants will use machine learning to forecast men’s tournament outcomes. 

This competition incentivizes match outcome predictions rather than the more typical game theory approach. Models should forecast win percentages of every possible matchup in the Tournament of 64—a total of 2016. (This does not include the First Four teams. Those matchups can be included, but they will not be considered as part of evaluation.) 

Registration is limited to US university students, with teams of up to three members. Participants will be provided with a training data set and external sources may be used as part of model development. Although Selection Sunday is not until March 17, you may begin model training immediately.
Now available in the data section is **final_deduplicated.csv** with columns 
•	*GameID*
•	*Team1*
•	*Team2*

Teams must edit and submit their own versions of this file, containing ONLY *GameID* and adding a column for *Team1WinPercentage*.

Teams are permitted one entry, which must be submitted by the start of the tournament on March 21. Winners will be announced shortly after the tournament ends, with prizes awarded to the top three teams.


Send any questions to ethan.goldberg@duke.edu