Pythia Sports, a data provider for the racing and igaming sectors, has launched an AI-driven solution aimed at enhancing the accuracy and efficiency of breeze-up horse sales. The tool is designed to support buyers in identifying standout two-year-old prospects during the key April sales season.
The technology uses a proprietary model that evaluates over 100 variables, including time, stride length, and biomechanics. By combining machine learning, AI, and historical sales data, the platform generates predictive ratings intended to inform purchasing decisions during auctions.
The new system was recently deployed at the Newmarket breeze-up sale, where it attracted interest from buyers and consignors. According to Stephen Davison, Pythia Sports’ head of commercial operations, the next implementation will take place during the upcoming Doncaster sale, with breezing scheduled for April 23 and the auction set for April 24.
The initiative reflects growing momentum in the racing sector to adopt data-led solutions to support commercial and sporting outcomes, with increasing crossover between traditional bloodstock sales and technology-driven analysis.
“The technology analyses three different sections of the breeze: the time, speed and stride profile, the model tracks each stride as the horse gallops combining it with sectional times,” says Davison. “That allows us to see how the stride profile changes as the horse accelerates and when it reaches top speed.
“We have biomechanics as well, that looks at the horse’s walk and takes measurements of a horse’s conformation and its gait. That works in conjunction with historic racing performances to learn what the most defining physical features are in an elite horse.
“For example we can go back ten years to look up breeze-up data to say, ‘this horse did this breeze, this stride and these biomechanics’ and then the machine learning model can start picking up stuff we’ve missed or things we’ve maybe underestimated or overestimated.”
“I think there’s definitely starting to be a lot more openness to people using data to inform their decision-making. You only have to look at where football was 10-15 years ago to where it is today. The obvious examples are Brighton and Brentford who were using their own player data models to find value in the transfer market way before any other top level club. It is only natural that you can get a cross over into other sports and other industries. We’re hoping we can play our part in revolutionising the way horse racing and bloodstock views the use of data within the sport.”
