Note: The Race Handicapping Option is useful for ranking many things, not just horses.
Neural networks are often used successfully to predict the outcome of a horse race or dog race. Input data may include data about a race that is the same for all horses (called common statistics, e.g., track conditions) as well as statistics on each horse. Each training pattern may include statistics on 8 to 10 horses in a race and the network will try to compare all horses at the same time. Actually, you can choose any number of horses.
This module will preprocess the data so that the network will be able to compare only two horses at a time (in other words, "explode" the file). This will simplify the network for training purposes and increase the accuracy of the predictions.
For more information, see Race Handicapping Prenetwork - Detail.
File Note: This module defaults to creating a .PAT file for further processing by NeuroShell 2. Once the network is applied to this file, the Race Handicapping Postnetwork module may be used to return the file to its original form of an entire field of 8 to 10 horses with a predicted finish place for each horse in the race. We call the prenetwork process "exploding" the file and the postnetwork process "imploding" the file.
You may also refer to Tutorial Example Three to see how to set up data, explode, train network, apply network, make predictions, and implode with the Race Handicapping Option.