But where would you even start discovery? I guess no one with a remotely useful idea wants to share it ...I did a bit of Googling after the article came out last year and apart from a few research papers and that Wired article about Joan Ginther, not much comes up.
I'm surprised he is openly talking about everything, but I suppose many others have caught up and there's not much to lose ...
If you know the business you can focus on one area. I had a friend who was a fanatic that specialized in workout performance. He was in his late 70s and would use twitter, forums and other sources to identify about a dozen horses that he would track tightly in the spring.
Then he'd go to Belmont in the Spring and basically live at Saratoga in the Summer. He'd watch workouts, assess the horses, watch the trainers and jockeys and gather various datapoints. I was skeptical at first, but he at a minimum made enough to live in Saratoga for the meet, which is not cheap, and funded alot of his toy purchases from his winnings. He'd call out of the blue give me picks that were good winners about 50% of the time.
Basically, there were two ways he made money -- he followed his dozen horses for the high quality stakes races, and was able to eliminate shitty horses for the lower quality races based on trainer or workout performance. For the low quality races, he would hit a few wins/exactas a week (exacta = bet on 1st and 2nd place), and for the higher quality races he would do more exotic bets (Pick 6, trifecta, exacta)
This guy loved horses, the track, and the people around it. He was a widower and had lots of time on his hands. Definitely a labor of love that kept him sharp for a long time.
There are a ton of papers on sports analytics. The public stuff isn't cutting-edge, most of the results about profitability are totally bogus but you will quickly understand what people at the cutting edge are likely doing. The great thing is though: you can start with a few thousand and bet in small markets, you don't need to do anything sophisticated there.
The big syndicates also aren't that secretive anymore. The founders and employees have got too rich (some are billionaires), and they have had to build a profile to hire (if you attended an elite uni in the UK, they recruit there...the largest syndicate in the UK has hundreds of programmers now).
And Bill has been talking about this for years. I don't understand why but he was publishing papers and giving talks in the 1990s. The impression I get is that he wants other people to know he is smart, and already has more money than he needs (this was true even in the 1990s).
Something that most people here won't get though: the models don't matter. The largest syndicates hire clever people but the real money is made in finding liquidity and people to take the other side. The big UK syndicates got large because they worked with bookies in Asia (the largest syndicate is run by someone who ran an Asian book) who needed people to take risk.
Yeah, that's the conclusion I am coming to as well. The people with good models aren't going to talk about them. Even if they need investment they'll seek it privately. I guess I was thinking of a market where you can 'invest' your money in someone's model and they take a percentage of your winnings (that's their incentive for adding your money to the pool). Then it's a democratised race for whoever has the best model.
In horse racing where the bets are done via parimutuel[1], the challenge is that there's an upper bound on how much you can "invest" in a given wager without changing the odds. This makes it less likely that an expert will seek outside investment unless their model has them betting "wide" (lots of small bets vs. a few large ones).
Lol. The people who have the best models are often billionaires, have funds that manage hundreds of millions, and will employ hundreds of people on their own dime...they don't need to make a percentage on your $1000 investment.
Btw, these websites already exist but no-one on there makes any money. You don't need a lot of capital to make money in sports betting (because you turn your capital over so many times a year), there is no reason for a good sports bettor to use those sites to publicise themselves.
Here's an idea from an Australian website where you can build a very basic model, using past results (which are of course no guarantee of future performance) and then sell it. Or alternatively, you can buy "qualifiers" for these systems for a small fee.[1]
I'm from Georgetown, KY / Lexington area (the horse capital of the world) and I have a program where I can input data from upcoming races, including weather predictions, that can simulate a potential race over and over, resulting in some meaningful numbers. It's a bit like a brute force training/ML approach. Data resulting from this approach is FAR more valuable than an actual bet.
I'm surprised he is openly talking about everything, but I suppose many others have caught up and there's not much to lose ...