Nearest-neighbor matchup effects: accounting for team matchups for predicting March Madness

Published in Journal of Quantitative Analysis in Sports, 2015

In this paper we analyzed march madness brackets, clustering the teams and then doing a random effects model.

The predictions are made for every future round of the NCAA basketball tournament.

The clustering allows sharing of information across teams whose characteristics are similar.

The paper received a fair bit of press when published, for example the American Institute of Physics (AIP) wrote an article about the paper.

Recommended citation: Hoegh, A., Carzolio, M., Crandell, I., Hu, X., Roberts, L., Song, Y., & Leman, S. C. (2015). Nearest-neighbor matchup effects: accounting for team matchups for predicting March Madness. Journal of Quantitative Analysis in Sports, 11(1), 29-37.
Download Paper | Download Slides