Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter February 24, 2015

A mixture-of-modelers approach to forecasting NCAA tournament outcomes

  • Lo-Hua Yuan , Anthony Liu , Alec Yeh , Aaron Kaufman , Andrew Reece , Peter Bull , Alex Franks , Sherrie Wang , Dmitri Illushin and Luke Bornn EMAIL logo


Predicting the outcome of a single sporting event is difficult; predicting all of the outcomes for an entire tournament is a monumental challenge. Despite the difficulties, millions of people compete each year to forecast the outcome of the NCAA men’s basketball tournament, which spans 63 games over 3 weeks. Statistical prediction of game outcomes involves a multitude of possible covariates and information sources, large performance variations from game to game, and a scarcity of detailed historical data. In this paper, we present the results of a team of modelers working together to forecast the 2014 NCAA men’s basketball tournament. We present not only the methods and data used, but also several novel ideas for post-processing statistical forecasts and decontaminating data sources. In particular, we highlight the difficulties in using publicly available data and suggest techniques for improving their relevance.

Corresponding author: Luke Bornn, Harvard University – Statistics, Cambridge, Massachusetts, USA, e-mail:


Boulier, Bryan L. and Herman O. Stekler. 1999. “Are Sports Seedings Good Predictors?: An Evaluation.” International Journal of Forecasting 15(1):83–91.10.1016/S0169-2070(98)00067-3Search in Google Scholar

Brown, Mark and Joel Sokol. 2010. “An Improved LRMC Method for NCAA Basketball Prediction.” Journal of Quantitative Analysis in Sports 6(3):1–23.10.2202/1559-0410.1202Search in Google Scholar

Bryan, Kevin, Michael Steinke, and Nick Wilkins. 2006. Upset Special: Are March Madness Upsets Predictable? Available at SSRN 899702.10.2139/ssrn.899702Search in Google Scholar

Carlin, Bradley P. 1996. “Improved NCAA Basketball Tournament Modeling via Point Spread and Team Strength Information.” The American Statistician 50(1):39–43.Search in Google Scholar

Cesa-Bianchi, Nicolo and Gabor Lugosi. 2001. “Worst-Case Bounds for the Logarithmic Loss of Predictors.” Machine Learning 43(3):247–264.10.1023/A:1010848128995Search in Google Scholar

Cochocki, A. and Rolf Unbehauen. 1993. Neural Networks for Optimization and Signal Processing. 1st ed. New York, NY, USA: John Wiley & Sons, Inc., ISBN 0471930105.Search in Google Scholar

Cover, Thomas M. and Joy A Thomas. 2012. Elements of Information Theory. John Wiley & Sons, Inc., Hoboken, New Jersey.Search in Google Scholar

Demir-Kavuk, Ozgur, Mayumi Kamada, Tatsuya Akutsu, and Ernst-Walter Knapp. 2011. “Prediction using Step-wise L1, L2 Regularization and Feature Selection for Small Data Sets with Large Number of Features.” BMC Bioinformatics 12:412.Search in Google Scholar

ESPN. 2014. NCAA Division I Men’s Basketball Statistics – 2013–14, 2014. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Friedman, J. 2001. “Greedy Function Approximation: A Gradient Boosting Machine.” Annals of Statistics 2:1189–1232.10.1214/aos/1013203451Search in Google Scholar

Fritsch, Stefan, Frauke Guenther, and Maintainer Frauke Guenther. 2012. “Package ‘Neuralnet’.” Training of Neural Network (1.32).Search in Google Scholar

Hamilton, Howard H. 2011. “An Extension of the Pythagorean Expectation for Association Football.” Journal of Quantitative Analysis in Sports 7(2). DOI: 10.2202/1559-0410.1335.10.2202/1559-0410.1335Search in Google Scholar

Harville, David A. 2003. “The Selection or Seeding of College Basketball or Football Teams for Postseason Competition.” Journal of the American Statistical Association 98(461):17–27.10.1198/016214503388619058Search in Google Scholar

Hastie, Trevor, Robert Tibshirani, and Jerome Friedman. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd ed. Springer.10.1007/978-0-387-84858-7Search in Google Scholar

Huang, Tzu-Kuo, Ruby C. Weng, and Chih-Jen Lin. 2006. “Generalized Bradley-Terry Models and Multi-Class Probability Estimates.” Journal of Machine Learning Research 7(1):85–115.Search in Google Scholar

Jacobson, Sheldon H. and Douglas M. King. 2009. “Seeding in the NCAA Men’s Basketball Tournament: When is a Higher Seed Better?” Journal of Gambling Business and Economics 3(2):63.10.5750/jgbe.v3i2.546Search in Google Scholar

Kaplan, Edward H. and Stanley J. Garstka. 2001. “March Madness and the Office Pool.” Management Science 47(3):369–382.10.1287/mnsc.47.3.369.9769Search in Google Scholar

Koenker, Roger and Gilbert W. Bassett, Jr. 2010. “March Madness, Quantile Regression Bracketology, and the Hayek Hypothesis.” Journal of Business & Economic Statistics 28(1):26–35.10.1198/jbes.2009.07093Search in Google Scholar

Liaw, Andy and Matthew Wiener. 2002. “Classification and Regression by Randomforest.” R News 2(3):18–22.Search in Google Scholar

Massey, Kenneth. 2014. College Basketball Ranking Composite. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Matuszewski, Erik. 2011. “March Madness Gambling Brings Out Warnings From NCAA to Tournament Players.” Bloomberg News, March 2011. ( in Google Scholar

McCrea, Sean M. and Edward R. Hirt. 2009. “March Madness: Probability Matching in Prediction of the NCAA Basketball Tournament”. Journal of Applied Social Psychology, 39(12):2809–2839.10.1111/j.1559-1816.2009.00551.xSearch in Google Scholar

MomentumMedia. 2006. NCAA Eliminates Two-in-four Rule. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Moore, Sonny. 2014. Sonny Moore’s Computer Power Ratings. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Platt, John C. 1999. Probabilities for SV Machines. MIT Press. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Pomeroy, Ken. 2014. Pomeroy College Basketball Ratings, 2014. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Ridgeway, Greg. 2007. “Generalized Boosted Models: A Guide to the GBM Package.” Update 1(1):2007.Search in Google Scholar

Riedmiller, Martin and Heinrich Braun. 1993. “A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm.” Pp. 586–591 in IEEE International Conference on Neural Networks.Search in Google Scholar

Sagarin, Jeff. 2014. Jeff Sagarin’s College Basketball Ratings, 2014. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Schwertman, Neil C., Thomas A. McCready, and Lesley Howard. 1991. “Probability Models for the NCAA Regional Basketball Tournaments.” The American Statistician 45(1):35–38.Search in Google Scholar

Smith, Tyler and Neil C. Schwertman. 1999. “Can the NCAA Basketball Tournament Seeding be Used to Predict Margin of Victory?” The American Statistician 53(2):94–98.10.1080/00031305.1999.10474438Search in Google Scholar

Sokol, Joel. 2014. LRMC Basketball Rankings, 2014. ( Accessed on February 22, 2014 and March 28, 2014.Search in Google Scholar

Tibshirani, Robert. 1996. “Regression Shrinkage and Selection via the Lasso.” Journal of the Royal Statistical Society. Series B (Methodological) 288:267–288.10.1111/j.2517-6161.1996.tb02080.xSearch in Google Scholar

Timthy P. Chartier, E. Kreutzer, A. Langville and K. Pedings. 2011. “Sports Ranking with Nonuniform Weighting.” Journal of Quantitative Analysis in Sports 7(3):1–16.10.2202/1559-0410.1290Search in Google Scholar

Toutkoushian, E. 2011. Predicting March Madness: A Statistical evaluation of the Men’s NCAA Basketball Tournament.Search in Google Scholar

Published Online: 2015-2-24
Published in Print: 2015-3-1

©2015 by De Gruyter

Downloaded on 4.2.2023 from
Scroll Up Arrow