Artificial intelligence (AI) and machine learning are at the forefront of a new pedigree analysis website which has been launched by G1 Goldmine founder Leo Tsatsaronis. The Pedigrees 360 software is intended for use in helping to predict the likely success of matings by focusing on “line-breeding clusters”.
“Using AI and machine learning, the programme has shown a very high degree of accuracy in predicting which pedigree combinations will produce the champions and which will produce the perennial maidens,” said Tsatsaronis.
“Most of the existing mating tools focus on nicks and crosses, which is a simplistic view of how a pedigree pattern influences the class of a horse. Deep line-breeding clusters are the foundation pattern present in the most successful breed-shaping stallions in the past 100 years. Some of the greatest breeding minds in history, such as [Federico] Tesio, the Aga Khan, [Marcel] Boussac, designed their pedigrees to build multiple clusters and multiple layers of key ancestors going back to eight and nine generations.”
He continued, “Most of these great breeders had the ability to 'see' deep line-breeding patterns, and their vision without computers was extraordinary.”
The software design for Pedigrees 360 includes nine-generation pedigrees for thousands of horses across a range of abilities, with the aim of finding the qualities that separate them. Tsatsaronis noted that it's as important to identify which mating patterns are unsuccessful, especially when those patterns involve fashionable pedigrees. He also points to the ability of Pedigrees 360 to identify potential quality horses from matings deemed unfashionable by the commercial marketplace, citing Knicks Go, North America's 2021 Horse Of the Year, as an example of what the software can find.
“Although the horse is the result of a mating involving a low-fee sire, and he sold for a low price at auction, Pedigrees 360 shows the mating had more potential than conventional wisdom might suggest,” said Tsatsaronis.
“The AI modelling analysed 48 identifiable clusters within nine generations, with clusters being items such as counts of sire duplications, counts of sex-balanced mare duplications at seven, eight, and nine generations, and inbreeding positioning between generations.
“Obviously, there are always going to be horses which belie their pedigree. Some which the programme suggests are going to be outstanding are actually slow, and vice versa, but so far these are proving to be a small percentage and maybe the result of some biomechanical factor rather than pedigree.”
He added, “When most breeders and buyers are assessing a prospective mating or yearling, they take a variety of factors into consideration, including, pedigree, conformation, x-rays and movement. Our programme is just a tool to assist in one of those factors but it is a very powerful tool.”
Hutton Goodman of Mt. Brilliant Farm is among the North American breeders who have signed up to Pedigrees 360. He said, “It's a very interesting tool that we are really starting to lean on, and the great thing about Leo's software is that you know he is going to keep sharpening it and updating it, making it more useful, like he did with G1 Goldmine. We have already started to see some of the great features he is developing to hopefully add, and it is exciting stuff.”
More information on the launch of the new website can be found via www.pedigrees360.com.
The post Artificial Intelligence Deployed in Pedigrees 360 Mating Planning appeared first on TDN | Thoroughbred Daily News | Horse Racing News, Results and Video | Thoroughbred Breeding and Auctions.
