Neural Network Prediction of NFL Football Games

Joshua Kahn ECE539 Fall2003

Overview
 

Introduction Work Performed

Data Collection Preliminary Study Training and Prediction Set Creation Data Preprocessing Making Predictions

 

Results Conclusion

Introduction


The National Football League (NFL) is a multi-billion dollar business Many web sites claim to be able to predict the outcome of NFL games Some of these sites are trustworthy, others are downright seedy Why are actually correct?

Project Goal


Most prognostications are based on human opinion

Invariably, some degree of bias enters in

This project aims to create a completely objective, statistics based system for predicting the outcome of NFL games
The trouble lies in the intangible aspects of the game It seems plausible to do create a statistical system

Why a Neural Network?



Teams can win in a variety of ways

No linear mapping exists to determine the outcome

This problem essentially boils down to a pattern classification problem

Neural networks are very good at solving these problems Neural network provides a non-linear mapping

Data Collection


Data was to be available from a typical NFL box score A large data set was required to represent the large number of ways to win Collected from NFL.com
Used Excels web query feature to acquire tabular data, such as box scores and team averages

Data Collection


Data was extracted from the box scores using a Perl script
Perl provides an Excel interface

Statistics could be selected from the box scores as desired

Perl also allowed additional data processing

Needed to determine which statistics to use

Preliminary Study


Data was analyzed using Matlab to look for dependency, redundant data, etc. No hyperplane exists to separate wins and losses based on statistical analysis

6 4 T urnover D ifferential

2 0

-2 -4

-6 -8 -400 2000 -300 1000 -200 -100 0 0 100 200 -1000 300 400 -2000 Tim e of P ossession D ifferential

Total Y ardage D ifferential

Preliminary Study Results



Determined the following statistics were most predictive:

Total yardage differential Rushing yardage differential Time of possession differential (in seconds) Turnover differential Home or away

Differential statistics provide insight into offensive and defensive performance Scoring data was excluded as it would bias the networks output toward a single feature

Training and Prediction Sets



Training sets include the statistics for both teams for each game Each training vector also includes the outcome of the game
Outcome marked for both teams 1 = win, -1 = loss

Two prediction sets were created:

One based on team season averages Other based on average of prior 3 weeks Both sets were applied to determine effectiveness

Neural Network Selection



Back-propagation multi-layer perceptron provides a great deal of flexibility

Good pattern classifier Supervised learning

Network parameters and structure were determined based on testing

Data Preprocessing


Processed all data using singular value decomposition

Gives additional weight to the most pertinent features prior to network input Makes training more effective

Performed using Matlabs svd function

Making Predictions
 

Trained network using training data Applied prediction data three times
Used both season and three week average to determine effectiveness of the two

 

Found the average of the three trials Classified winner/loser of game

Winner had higher network output

Results
Week Week 14 Week 15


Prediction Rate Season Average Three Week Data Average Data 75% 62.5% 75% 37.5%

Neural network classification correct 94% when actual (not predicted) statistics are used NFL teams seem to be consistent over the long-term

Results
Week 14
Green Bay def. Chicago Philadelphia def. Dallas Indianapolis def. Tennessee San Diego def. Detroit Tampa Bay def. New Orleans Baltimore def. Cincinnati Jacksonville def. Houston Pittsburgh def. Oakland Minnesota def. Seattle New York Giants def. Washington

Week 15
Indianapolis def. Atlanta Kansas City def. Detroit New England def. Jacksonville New York Jets def. Pittsburgh Cincinnati def. San Francisco Denver def. Cleveland Dallas def. Washington New Orleans def. NY Giants Tennessee def. Buffalo Tampa Bay def. Houston Minnesota def. Chicago St. Louis def. Seattle Oakland def. Baltimore Carolina def. Arizona Green Bay def. San Diego Philadelphia def. Miami

San Francisco def. Denver def. Kansas Arizona City New England def. Miami Atlanta def. Carolina Buffalo def. New York Jets St. Louis def. Cleveland

Baseline Study
Prediction Rate Week Week 14 Week 15
 

Neural Network 75% 75%

ESPN.com 57% 87%

Neural network was more accurate on average Previous neural networks predictors accurate for 63% of games

Conclusions
Game Misclassification Reasoning


Of eight misclassifications, each can be subjectively identified in one of 3 categories

Philadelphia def. Dallas Misclassification San Diego def. Detroit Atlanta def. Carolina Minnesota def. Seattle New England def. Jacksonville New York Jets def. Pittsburgh Cincinnati def. San Francisco Oakland def. Baltimore Too close to call Upset Too close to call Misclassification Too close to call Too close to call Upset

Conclusions


Prediction rate could be improved by adding the human element

Take immeasurable into consideration Las Vegas betting lines Subjective team rankings

Training set could be based on previous season data

Ways in which teams win presumably does not change over time

Proves that a statistically based system can be developed to predict outcome of NFL games

References
Haykin, S. (1999). Neural Networks: A Comprehensive Foundation. Upper Saddle River, New Jersey: Prentice-Hall, Inc. ESPN.com, http://www.espn.com [Retrieved Dec 2003]. Purucker, M.C. (1996) Neural Network Quarterbacking. Potentials, IEEE, vol. 15:3, pp. 9-15. NFL.com, http://www.nfl.com [Retrieved Dec 2003].

Questions???

Thank you