California Racing Has Always Been an Island

By now everyone's read the Drape story about Triple Crown winner Justify receiving an alleged (no one has disputed it yet, so maybe they'll drop the alleged part soon) positive test for the drug scopolamine.

This drug is not new to horse racing, as over the years positives have resulted in trace amounts (through contamination) where trainers are held accountable. But, as the data has come in, it has been studied, and jurisdictions around the world have set limits on the amount of the drug that can, according to the science, be attributed to the environment.

In Louisiana, it's 75 ng/ml, Europe 30 ng/ml.

The International Federation of Horse Racing Authorities has the contamination limit at 60 ng/ml.

In Australia, it's 25 ng/ml. 

Justify's test, according to Drape, showed 300 ng/ml.

California seems - at least some protagonists do - to think 300 mg/ml can still be a contaminant.

This leads to a broader discussion about uniform rules on drugs and suspensions. Let's face it, that should've been done an epoch ago; uniform rules are directly proportional to fewer regulatory clown shows. But, for whatever reason, California racing does not seem to take heed. It does what it does.

I've always felt it's why the general public doesn't much understand horse racing.

To your average Joe or Jane, this reads fairly simple. It's a case of a 0.08 blood alcohol limit for drunk driving because everyone agrees that's proper. But in California, a guy who blew a 0.12 was let drive home because someone arbitrarily decided he's a big dude and he said he drank some mouthwash. It just doesn't compute.

Have a nice Thursday everyone.

Can We Beat the Computer Horse Betting Models? At Times, Sure We Can.

On a previous post I mentioned a book I read a couple of weeks ago called "Digital Marketing in an AI World" and promised a couple of thoughts on AI or big data models for horse racing.

If you're interested I'll share a few of those thoughts below.

First, I'm a believer in modeling for sports betting and racing, because with proper discipline, some smarts, and a malleable model we can make hay when the sun shines. Numbers remove bias, and they take away what we thought we knew, but really never knew out of a wager. A good model, even in horse racing's high rake environment, can work, and work pretty well.

When we analyze data in horse racing a few characteristics generally occur.

i) We learn pretty quickly how difficult the game is to beat. The angles we thought were great, aren't great at all (unless you like losing 15 or 20 cents of every dollar you bet). When you run a model on a subset of (statistically significant) data, the chances of it showing +EV are slim. When you parse or layer too much, you're chasing your tail with bad information.

ii) The horses a model may signal as plays are pure overlays, and some of these horses - on paper - will look gawd awful. We'll see an 0 for 11 horse, a bad jockey switch, terrible form - what we may call 'qualitative anti-angles' - that make us not want to wager on the animal (which is precisely why these wagers can approach 1.00 ROI).

iii) the price of the horse (or the bet type) is everything.

The teams we read so much about are doing much of the above religiously. Can we beat them? In my view, Fred's book tells us one way how.

Self driving cars are in the news, sometimes for terrible reasons. When an accident occurs, it sheds light on the problems with AI, and in-turn, some of racing's computer modeling.

This AI works on a three-step process - perceive, plan and execute. In Tempe, Arizona last year, this was on display, and not in a good way.

A woman was walking her bicycle across a four lane highway after dark and was struck and killed by a self driving car. The car's LIDAR perceived a human with a bicycle, but in the planning stage it computed it could not be a human with a bicycle because it's a 4 lane highway at night. In the execution stage the AI asked "what should we do?" and the answer was, "keep going."

Fred writes: "Machine learning systems can make mistakes, and it's possible to outflank the competition by capitalizing on them."

In racing, in my view, we see this often.

Several years ago I remember playing the Woodbine polytrack for the first day of the meet. Like other computer modelers I knew the poly is fast, and horses who make the lead are great bets. At times, even with bad trainers or riders, you could make a score. But, at least one modeler was slow to the draw.

At Woodbine, the fifth race had a horse who my model said would make the lead, and horses who made the lead were 4 for 4* already. It was a green light. But one bot, run on a model, didn't agree. Whether it was working with late pace numbers, didn't have a built-in bias, or what I do not know, but it just kept fading the animal. It was 6-1 on the board 14-1 on the exchange, then 16-1, then 17-1. I kept putting up cash, wondering what in the hell price this model was working on. It took the offers up to 25-1. The horse won easily and paid $18.

The above is not as isolated occurrence.

What other mistakes do we see?

In my view - lame horses. If you're an old school horse watcher, you can take these models to school, using the model itself - perceive, plan, execute. Did the horse look like this last time? No, then execute, because that model betting $1,400 on its nose likely has no clue.

I have seen horses head to the gate lame who were gate scratched that the models were on. They're losing money, so we have to be the one to beat them.

Overall, I am certainly no expert, but I love modeling and models, for horse racing or otherwise. They work. But, it doesn't mean they can't be exploited. Those are a couple of areas I think they can be had.

Have a really nice Friday everyone.

* My top pace figure (with a slight speed track modification) went 10 for 10 that day. It was a rare Let It Ride type day that keeps a lot of us coming back. 

The Tantalizing Touts

@bvalvsracing tweeted out a nice article last week about the touts. It talks a great deal about entertainment content versus hard-edged +EV predictions. Namely, it pays to tout for entertainment purposes, because it's sexier. That's why we see a lot of content presented like this -

“The wrong team is favored and I love this team as a home underdog. They are coming off extra rest and the defense has been impenetrable so far this season. I will be taking them on the money line and expect them to win the game.”

You and I know the obvious - that information is already considered in the line, so it's kind of useless. But if that team performs well, then this tout is off to the races.

Meanwhile, for the +EV dude or gal, they're off in the tout wilderness with their analysis.

“Due to many factors and variables within the model, we have the home team priced at -9.75 with a current edge over the market price of x%, being our biggest edge even after regression back to the market price. Also, I see variations in price/spread from -6.5 -120 to -7 +105 and a few other prices across the screen so it will also depend on how much you value 7 in today’s NFL and what outs you have among other considerations.”

Zzzzzzz.

Horse racing represents this phenomenon a lot.

"Chad Brown wins with shippers from overseas in routes."

Thanks, that's why the horse is 6-5.

However, unlike in sports betting - where you do see the second kind of content - in horse racing there is very little. The HANA Horseplayer Magazine had some, you'll find a little on twitter now and again. But it's pretty much a dearth.

I think there are a couple of reasons for it - i) most profitable players keep their oddslines and angles a secret, and ii) there is almost no market for this analysis in horse racing; math players aren't trying to beat 20% juice in horse racing in some six horse field scattered almost minute by minute on any given day.

Another point that struck me while reading the article. The tantalizing touts, with angles, and all the rest can make hay in sports, because if they are not horrible people will win enough over a season to keep firing. You only have to beat 4.8% (or lower if you line shop) takeout. I think that's why we see so many of them. It's difficult to break even over a season (no offense to them, they are just doing their jobs) playing TVG host pick 4 tickets.

Have a nice Wednesday everyone.