Can Artificial Intelligence, ChatGPT, Predict the Kentucky Derby Winner?
In 2022, the Kentucky Derby saw a shocking upset by 80-1 longshot Rich Strike that even an advanced artificial intelligence program would be hard-pressed to predict. With the advancement of technology, many are curious if artificial intelligence can forecast the outcome of horse racing events. To test this theory, we employed the A.I. chatbot ChatGPT to predict the winner of the Kentucky Derby.
Limitations of ChatGPT
Open up ChatGPT and ask it to project the winner of the Derby, and you’ll instantly receive a message denying your request. As the A.I. program will tell you, it cannot predict future events or provide information beyond its knowledge cut-off date of 2021. However, there are many factors that affect the outcome of the race, including the skill of the jockey, track condition, health of the horse, and weather.
Building a Predictive Model
To test whether certain factors could predict the winner of a previous Derby, we began working backward with ChatGPT to teach it how to learn various data points and create a model to test which horses had the highest probability of winning in the past. We utilized information such as the full field, post positions, trainers and jockeys associated with each horse at the time of the Derby, historical win percentages of each post position, past performances in graded stakes, Brisnet Speed figures, and trainer and jockey information.
The Results
Upon running 1,000 simulations, one name in particular stuck out - Bellamy Road was named the most likely winner of the 2005 Derby, but 50-1 longshot Giacomo recorded 105 wins in the simulation. When running 10,000 simulations, Bellamy Road remained the most likely winner, while Giacomo's highest probability of winning was 6.22%, which ranked him as the fifth most likely winner.
Limitations of Artificial Intelligence
It must be noted that A.I. may help you pinpoint a winner of the Kentucky Derby, but it comes with a caveat. You will need to feed the A.I. the necessary data in order for it to produce a predictive model. Even then, there may be inaccuracies in the system. Knowing which data is most important to predicting the winner of the Kentucky Derby is also a challenge. In the end, it is still important to dedicate time to building a predictive model through A.I.
Overall, the use of artificial intelligence in horse racing is still a budding field and it remains to be seen how much of an impact it will have in the future.
