Skip to content

Using a neural net to predict how horses in Hong Kong will finish in races.

Notifications You must be signed in to change notification settings

bleech1/PredictingHorseRaces

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PredictingHorseRaces

We create a model to predict whether or not a horse will show , ie finish first, second or third, based on data from Hong Kong horse races. We use features based on the track and conditions, the horse itself, as well as more advanced features such as an indicator variable that describes whether the horse is the race's favorite and a variable that measures if the horse is racing in a longer horse than it has recently been running in.

To run, first run ModifyData.py to add the user-created features to the dataset, as well as shuffle the values in the dataset. Then, run PredictHorses.py to create and run the neural network, as well as get the winnings from gambling using this model.

Work.py was made when we changed our problem to predicting whether a horse would show or not before completely changing our codebase. TrainModel.py and PredictHorses.py are the same code.

About

Using a neural net to predict how horses in Hong Kong will finish in races.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages