“When a young horse enters the stud he should be judged, first, his class as a racer; second, by his physical attributes; third by his pedigree.” Joseph Estes, November 10, 1934.
Since the time when the Sport of Kings was literally, the sport that kings participated in, thoroughbred breeding has been a non-random event, based on the belief that there is something to gain from the selection of mates that could not be obtained by random selection of mares and stallions. A racehorse must be fast, but above all, it must be able to adapt to the particular conditions prevailing in each event. This makes the actual performance of one thoroughbred somewhat difficult to define as it is relative to competition and circumstances of this competition that it faces on the given day rather than time or any other constant metric.
Despite the fact that breeding and racing of thoroughbred horses has been a well-organized industry for well over a century now, it is a poor reflection on the industry at large that it has not yet come to an industry wide understanding of the best measures of racing performance or ability, the degree of inheritance of racing ability, and finally its failure to embrace statistical analysis and/or genomic breeding values as both a method of selection and to improve the breed as a whole. Famed geneticist Bertrand Langlois stated this issue clearly, “Why should one pay more for this or that pedigree or high performing sire if the performance (itself) is not heritable?”
While the Thoroughbred has operated under a closed stud book for over 300 years, there still exists a lot of variation between individual horses depending on what the desires of the racing environment are to achieve. Horses in Australia, as a general rule, are more likely to be sprinter-milers, a by product of having a lot of their prize money associated with early two-year-old racing. Conversely, the Japanese racing environment rewards distance runners at 10 furlongs (2000m) or more. As a result, their horses tend to be different physically as well as genetically.
It is these differences that make creating one model to predict the performance of an animal difficult. While each of the tests that we do can discriminate elite from non elite, even within that there are some horses that are more predictable than others which makes determining elite status on an ad-hoc basis a difficult thing to achieve.
In the pages that follow you will see how we bring together big data, genetic markers, phenotypic and biomechanical measurements in a way to reduce these variables and get to a more predictable type of horse, whatever the desirable outcome is.