With Chat GPT, AI, and machine learning making more considerable advancements over the last few years, can it help you win your March Madness Bracket Challenge?

In 2021, Will Geoghegan sure hoped so! After training a machine learning model to fill out his bracket, Geoghegan’s men’s bracket was still intact and in the top 0.2% of more than 14 million brackets on ESPN.

Geoghegan told Sports Illustrated he “used AdaBoost, which he said is essentially ‘an algorithm for combining a collection of relatively weak predictors into a single strong predictor.’ He pulled data from the Massey Ratings instead of using player or game-level data.

Essentially, the model aggregated the opinions of experts who create the college basketball rankings. It used the seeds and the various ranking systems as weak predictors with training data going back to 2003.”

Akkio, an easy-to-use, scalable, and affordable no-code AI platform for real-time decision-making, notes, “the strength of any machine learning model is entirely dependent on the quality of historical data you use to train the model. With an application like basketball, there is plenty of data, - so the upfront work was both choosing what data to include in the model and then building the dataset.”

Every year, more and more bracket challengers try to use data to their advantage for predicting the winner of March Madness, but AI predictions have been all over the place in success in the past:

In 2021, one AI prediction had Ohio State winning it all, who then lost in the first round. Another AI prediction had Gonzaga and Baylor in the championship game, with Gonzaga winning it all when in reality, Baylor won it all.
In 2022, AI predictions chose Gonzaga Bulldogs, Kentucky Wildcats, Arizona Wildcats, and Auburn Tigers to make it to the Final Four. In reality, the Final Four came down to the Kansas Jayhawks, Villanova Wildcats, North Carolina Tar Heels, and the Duke Blue Devils.

With continuous tinkering on what data should be used to create predictions, various models, and evergrowing technological advancements, can AI predict the 2023 National Champion? Here are some AI predictions for this year’s tournament:

Prediction 1: Kentucky is set to win it all against Iowa 84–79 in the National Championship.
Prediction 2: Creighton Bluejays, Houston Cougars, Duke Blue Devils, and the Kansas Jayhawks for the final four, with the machine picking Houston as the National Champion.

What are your thoughts on the above predictions for this year’s Men’s National Champion? Who do you have winning it all?