Predictive Horse Race Handicapping Using Neural Networks Semester Report

1
Predictive Horse Race Handicapping Using Neural
NetworksSemester Report

• Andrew Schurr
• Advisor Ralph Morelli

2
Overall Goal

• Use a neural network, trained with past
  performance data, to predict future horse races.

3
Picking Horses

• The outcome of a horse race is determined by many
  factors
  
• If we know what factors are important, we can
  predict which horse is favored to win
  
• This raw information is available as past
  performance data

Factors Previous race times Post position Jock
ey win/loss record Previous stakes Type of runne
r
Breeding ect
4
with Neural Networks

• By using a computerized neural network, we can
  sift through a large amount of computerized
  past-performance data, and identify which factors
  influence a winning horse
• Neural network
• Interconnected nodes that fire when stimulated
• Can learn through training, gradually adjusting
  the level at which they fire
  
• Good at figuring out how different variables
  influence each other

5
Topology
Inputs
Output
Previous race times Post position Jockey win/los
s record Previous stakes Type of runner Breedin
g
ect
Relative fitness of the horse
6
Current Progress
- Completed -
- Pending -
Find flexible java library for building Neural
Networks Build prototype that mimics small-scale
handicapping problem Locate a large set of digita
l past performance data Add small set of actual d
ata to prototype Clean and format full set of hor
se data, add to prototype Use genetic algorithms
to determine optimal neural network
configuration Build user interface and file loadi
ng capabilities on top of the fully-trained
network
7
Software Library

• Joone Java Object Oriented Neural Engine
• by Paolo Marrone
• Contains libraries and class files for building
  and training networks
  
• Backpropagation, Kohonen maps, ect.
• Full java source
• Accepts plaintext, Excel input files
• Handles training of network

8
Raw Data

• Data purchased from Handicappers Daily, ITS
  Inc.
  
• Comma-delimited text format
• Contains all publicly available data for each
  race
  
• Data formatted for Joone using Excel macros
• Prune unused data
• Normalize numbers (1 to 15 ? 0.0 to 1.0)
• Flatten into single-race rows

9
Raw Data
10
Trial with Limited Real Data

• Input data
• 12 horses per race
• Positions and fractional lengths for each horses
  two previous races
  
• Speed rating for each horse
• Output data
• Finish position and lengths for each horse
• Training
• 21 training races
• 4 test races
• 20,000 training cycles

11
Performance

• Training
• Training error 17-18
• Represents numerical error, not error in picking
  winners
  
• Prediction
• 0 correct winners picked
• 42 of horses correctly predicted to show
• but none in their correct positions

12

• (demo)

13
Sources

• Neural Networks for Fun and Profit, Bret Halford,
  http//csel.cs.colorado.edu/cs3202/papers/Bret_Ha
  lford.html
  
• An introduction to neural networks, Andrew Blais
  and David Mertz, IBM developerWorks,
  http//www-106.ibm.com/developerworks/library/l-ne
  ural/
• Expert Prediction, Symbolic Learning, and Neural
  Networks An Experiment on Greyhound Racing, H.
  Chen, P. Buntin, L. She, S. Sutjahjo, C. Sommer,
  D. Neely, http//ai.bpa.arizona.edu/papers/dog93/d
  og93.html
• Using Machine Learning To Predict the results Of
  sporting matches, Michael Baulch,
  http//innovexpo.itee.uq.edu.au/2001/projects/s348
  234/thesis.pdf
• Albrecht, http//www.teco.uni-karlsruhe.de/albrec
  ht/neuro/html/
  
• Handicappers Daily, ITS Inc., http//www.itsdata.
  com/
  
• Betting Thoroughbreds, Steven Davidowitz, First
  Plume Printing, 1997