Equibase’s New Ratings System Launches Saturday. Is It Ready?

[Wandering Eyes]

This Saturday at Santa Anita could prove something of a watershed moment in North American horse racing-the carding of two handicaps built upon a new national ratings system.

One race, a $35,000 handicap over 6 furlongs for dirt horses rated between 70 and 79, has drawn seven entries. The next race on the card, a $65,000 handicap over 6 1/2 furlongs on the hillside turf course for fillies and mares rated between 80 and 95, has drawn six entries.

The impetus for launching a ratings system in the U.S. has been well documented. Aside from helping racing secretaries card a suitable set of races for their backstretch inventory, such a system gives the connections of a claiming class of horse options to run without fear of losing it.

One thing it's not designed to do, those familiar with the system stress, is replace these claiming races, which has long proven the backbone of the U.S. product.

While North American is one of the last major jurisdictions to use such a ratings system, it appears to be the first to use an algorithm to generate the numbers (the others use human handicappers).

“It's novel to my understanding,” said Chance Moquett, senior manager of strategic solutions at Equibase, the company responsible for building the algorithm. “I believe it's the only algorithmic rating of a population of racehorses in the world right now.”

For any such system to work, however, the industry needs to have trust in it.

“There's no right or wrong way. But the right way is one that works and people have confidence in,” long-time track executive Rick Hammerle told Steve Byk's radio show last Thursday. “You're only as good as the number.”

Hammerle was involved in the building of a previous iteration of the ratings system which fell by the wayside earlier this year, but not with the version that has just launched.

According to Moquett, Saturday's ratings-based races are part of a soft launch of a system meant to be refined and improved over time and with experience.

“It's not necessarily a polished thing at this point in time. We wanted to make sure that we are continuing to work on it, and that people understand that,” said Moquett.

“Feedback is important,” Moquett added. “Feedback in any form is good feedback.”

 

The Building of the System

Since February, around 40 to 50 industry stakeholders within four different “cohort” groups have been working on the system, said Moquett, estimating around “50 formal meetings” as it came together.

These four groups comprise the worlds of data science, competition (including trainers and track executives), handicapping and wagering, and the international community.

In April, the racing secretaries from 12 different tracks or jurisdictions sent to Equibase a batch of around 20 horses for the team to rate.

(The 12 participating racing offices were at Keeneland, Churchill Downs, Gulfstream Park, Maryland, Oaklawn Park, Sam Houston, Prairie Meadows, NYRA, Canterbury, Assiniboia Downs, Del Mar and Santa Anita)

“Then we would give back the ratings and ask, 'how does this look? Does this look right?' We worked with each one of those racing offices individually,” said Moquett.

That process took a couple months. And then, when Equibase “felt like all the regional racing secretaries were largely pleased with how their selected bands seemed to seem to be rated,” they went back to test five years-worth of data on an individual yearly basis, said Moquett.

“That means we took every horse and ran it through a ratings history process for each race,” said Moquett. “We basically re-ran every race for every horse for the calendar year 2020 forward, caught out any outliers.”

What were some of those outliers?

“We did correlation analysis between purse earnings versus what their figure was at any point in time, to make sure the horses that generally were earning more money were in line [ratings wise]. And we identified that our turf horses seemed to be rated a little bit higher at first,” said Moquett.

More broadly, “I think another thing that we found, our rating was a little more volatile to surface switch and performance, and it had a hard time differentiating good horses from the elite level,” said Moquett.

The modified result is a multi-factor algorithm that gives horses a numerical rating (from 0-150) based on performance metrics, race class adjustments, surface and distance factors, track-specific variability, and recent form.

For a horse to be rated, they must have at least two North American starts. It's updated daily to reflect ongoing race results, so, even if a horse remains in its stall, its rating might fluctuate as its former rivals go out to compete.

The formula is based on three main buckets, with the “performance score” providing the core of the ratings.

“This has a litany of other factors peppered into it, but in essence, it's how fast did a horse run and how many lengths did it win or get beaten by,” said Moquett.

The second is the “race strengths adjustments” component, which looks at things like the class of the race and field strength. The “track and distance adjustments” factor in information like track variance and bias, as well as post position.

(A breakdown of the formula can be found here in an FAQ of the new system)

The computer algorithm won't be open-sourced-Moquett pointed to the proprietary nature of the system. That said, “we welcome people to come under the hood, see what's going on,” he added.

The theoretical ceiling is 150. “I think the highest rating we had during the annual testings was Flightline, who was 136. That's the highest it's ever gotten,” said Moquett.

One thing stakeholders should bear in mind, Moquett stressed, is that a numerical rating is different from a speed figure.

“A speed figure looks largely at time components of a single race,” said Moquett. “Whereas the Equibase rating takes the body of work in totality and grades aptitude.”

As to how the rating stack up to a corresponding weight, that will be up to the individual jurisdiction. “This is not a handicapping tool, nor is it something that Equibase is trying to force on any institution,” Moquett explained.

“We do not know yet how close or competitive these things are going to be from a weight standpoint,” Moquett added. “We are intentionally leaving that to the racing offices and the racing secretaries to do as they see fit.”

 

Actual Numbers

For those horses eligible for a rating, these numbers have already been displayed on their Equibase page.

While some ratings have raised a few eyebrows, in some cases there appear to be explanations. Take leading middle-distance turf runner (and dual Breeders' Cup winner), Rebel's Romance (Dubawi), rated 90.

In comparison, the four-year-old filly Antifona (Recoletos), whose entered in this Saturday's handicap on the downhill turf, is rated 95. Antifona is a stakes-winner who has not yet won a graded stake in three tries.

For one, Moquett admits “we are not very good yet at international play.” Furthermore, the Godolphin runner has only had one run so far this year in North America.

As Moquett puts it, the algorithm is more accurate the more recent North American starts a horse makes. “We reward consistent activity” said Moquett.

In comparison, Antifona has not had a single start in 2025. But the algorithm also factors in the frequency and quality of official works. In Antifona's case, she boasts a busy work-tab leading up to her first run in over 14 months.

“Her rating says this filly's working and working well. The last time she ran she was fast. And so, that's how this thing sees it,” said Moquett, explaining Antifona's 95-rating.

“Right out the gate, we've got a horse coming off a 14-month layoff,” Moquett added. “Did we give that horse enough of a negative impact or not enough of one? We'll learn. If she wins the race by five lengths, I'm going to feel like we did not do a good job.”

Another frequently raised example concerns top three-year-olds Sovereignty and Journalism, who have butted heads twice this year. Both times the Godolphin runner came out on top. And yet, Journalism is rated 104 while Sovereignty is rated 103.

“The algorithm isn't saying that Journalism is head and shoulders above Sovereignty. They're relatively equally matched all things considered,” said Moquett. “What makes sense whenever you actually look at the form is our rating gives a little bit of extra credit for Journalism running against older horses in the Pacific Classic,” said Moquett.

“What I would challenge people to think about is that we're not saying that horse A is faster than horse B,” Moquett added. “What we're saying is that we believe those two horses are relatively evenly matched within so many points.”

The “loudest glaring mistakes” are most likely “fringe players on our rating system,” said Moquett, adding that the system build out so far has focused primarily on the population of horse most likely to fill races, typically at the lower end of the rating range.

Attitudes towards the new system among Santa Anita's backstretch community has varied wildly. But if there's one main throughline, it's perhaps one of wait-and-see.

“I'm not sure exactly how it's going to work here yet,” said trainer Sean McCarthy. “But I don't have an issue with it. It's one way to keep onto a horse.”

“I don't feel like so far I have a great understanding of it. We're just feeling the water out,” said trainer John Sadler, who has Topalo (Tapiture) entered in the dirt handicap. “It's interesting. But it doesn't change the reality of California [a shrinking horse population].”

With the launch looming, another question being asked is this: is the system ready?

“We'll find out Saturday,” replied Moquett. “I think there's consensus in the industry that a new type of race and a new alternative to run horses is needed.”

He added, “I would rather have something delivered and work through a soft launch with racing offices during a time of need-be able to better manage a horse population-than be able to say I can answer every question and defend every example that you bring me because I don't know that we'd ever get to that.”

The post Equibase’s New Ratings System Launches Saturday. Is It Ready? appeared first on TDN | Thoroughbred Daily News | Horse Racing News, Results and Video | Thoroughbred Breeding and Auctions.

View the full article