[HN Gopher] Revisiting the algorithm that changed horse race bet...
___________________________________________________________________
Revisiting the algorithm that changed horse race betting (2023)
Author : areoform
Score : 99 points
Date : 2025-05-27 10:03 UTC (12 hours ago)
(HTM) web link (actamachina.com)
(TXT) w3m dump (actamachina.com)
| elpakal wrote:
| > Four of the five seasons resulted in net profits, the loss
| incurred during the losing season being approximately 20% of
| starting capital. A strong upward trend in rate of return has
| been observed as improvements were made to the handicapping
| model.
|
| For anyone interested in the results
| tlyleung wrote:
| Author here - funny to see this posted after a few years. Happy
| to answer any questions!
| fidotron wrote:
| Great write up. [am idiot]
| 4gotunameagain wrote:
| Please read the first paragraph of the post again. The
| original author of the paper is Bill Benter, and the GP is
| the author of this excellent writeup.
| tlyleung wrote:
| Sorry - to be clear this is just re-running the model
| detailed in Bill Benter's 1995 paper (he uses the time period
| 1986-1993) on more recent time periods (1996-2003, 2006-2013,
| 2016-2023) using PyTorch.
| jeffreyrogers wrote:
| How did you choose the artworks for the artworks section of
| your site?
| gosub100 wrote:
| Keep in mind if you found a profitable algorithm today, you would
| have to put a lot of care into concealing your bets. Casinos in
| the US will ban you from playing if you consistently win. And if
| they catch you structuring your bets they can deny your payout on
| winning tickets. You might get away with it for a year or so, but
| in any sportsbook, if they see your face daily and figure out
| you're consistently winning, (and not just playing for
| entertainment) don't expect it to last.
|
| Edit: this was a great video about online casinos and several
| accounts of people who were blocked for winning too much or
| structuring at in-person casinos:
|
| https://youtu.be/unksvJ1JfDE?si=u1tUH285geBykfrC
| UpAndAdam wrote:
| Horse racing differs from most sports betting in the US because
| it predominantly uses pari-mutuel wagering where the house
| takes a fixed percentage of each wagering pool. Accordingly,
| the house is incentivized to encourage bettors to place larger
| bets, since their piece only grows.
| gosub100 wrote:
| True, but it detracts from the enjoyment of everyone else by
| reducing payouts if algo players come in. Why place a bet on
| a multi-race jackpot if you know you're going to share it
| with multiple algo bettors? Why stand in line at the kiosk or
| sports book to play for fun if you have to wait exceptionally
| long because an algo bettor is boxing a bunch of picks and
| taking a long time? The longshots won't pay as much either
| because an algo will signal a positive EV. They're less
| likely to buy drinks or racing forms too.
| mathattack wrote:
| The inefficiencies eventually get "found out" by the algo
| traders and they compete away the alpha. Eventually they
| start losing money because of the house's edge.
|
| The house loses if all the suckers are driven out, and it's
| just algo, because then the algos leave.
| sitkack wrote:
| So the suckers are the ones injecting liquidity into the
| market?
| skippyboxedhero wrote:
| It doesn't, more efficient lines = better odds for punters.
| That is why Pinny/Asian books have better odds. The worst
| experience for gamblers is one with significant government
| intervention and/or limited professional involvement
| because there is no price discovery. Bookies don't just
| return that value to customers, in practice, they spend it
| on wildly expensive marketing, this means they have to
| offer lower payouts, and then spend inordinate amounts of
| time and money stopping professionals picking off their
| shitty lines.
| primeradical wrote:
| The algo bettors aren't using kiosks at the track. They're
| using dashboards and monitoring live video feeds. At least
| in my experience in the US.
|
| Most of the serious younger bettors are feeding daily form
| PDFs into an LLM and getting analysis, and placing bets
| using custom apps, rarely using UIs from the larger ADWs
| (advanced deposit wagering company). Older bettors are
| using phone wagering for larger bets.
|
| There is never a shortage of kiosks available for casual
| fans. Most tracks are either owned or partnered with ADWs
| that all have mobile apps, or sites for placing wagers, and
| casuals are encouraged to use those as they're more sticky
| after they leave the track.
|
| Even if algo bettors are influencing the odds because
| they're throwing money around, the house doesn't care
| because its percentage cut is the same (parimutual), and
| the casuals aren't bothered because they can't even tell
| what's happening.
|
| The totes are the ones analyzing fraud and abuse, and they
| don't care what tea leaves you read to place bets. They
| just care about avoiding government oversight and ensuring
| profits for the ADWs and tracks.
|
| Source, formerly a SWE for an ADW
| nikcub wrote:
| There is a professional gambler in Australia[0] who has the
| betting companies _compete_ for his business and offer him
| rebates on volume. His firm is double-digit percentage of the
| Australian betting market and employs ~hundreds of
| professional traders, developers etc. (it operates no diff to
| a hedge fund).
|
| As an aside - it was his firm that was responsible for the
| recent "breaking" of the Texas lottery[1]
|
| [0] https://en.wikipedia.org/wiki/Zeljko_Ranogajec
|
| [1] https://www.houstonchronicle.com/news/investigations/arti
| cle...
| plantain wrote:
| The opposite is true - the betting companies want algo traders
| to come and make the markets for them. They get reduced fees
| and bonuses for making the market.
| skippyboxedhero wrote:
| This isn't true. Very few places in the US run their books
| this way, and those that do limit your bet so most large
| bettors are still using beards. If you bet with someone who
| is moderately capable, for example Pinny, they will limit you
| then use your bets to reverse-engineer your strategy. Asian
| books are the only place where you can get action and, now,
| certain syndicates have become so large and dominant that
| they open lines earlier just for them. If you are only
| betting on outcomes, it is very hard to beat a line set by
| syndicate.
| bitshiftfaced wrote:
| This reminds me of an anecdote out of one of Thorp's papers
| (2007). He joined forces with a computer science Ph.D and started
| sports betting. They were very profitable, but he listed three
| reasons why he stopped: 1) it required having someone in Vegas
| placing bets, 2) he believed it was risky to have someone going
| around with large amounts of cash in order to make bets, and 3)
| it wasn't competitive with his stock market trading strategy. He
| mentions how his belief about #2 unfortunately turned out to be
| correct, as apparently something happened in another group's
| operation.
| AnotherGoodName wrote:
| I'm always skeptical of these "i totally made money gambling i
| just stopped for other reasons" type of claims and for good
| reason.
|
| Looking him up it looks like he managed to start and
| subsequently close (due to low returns) hedge funds.
| https://en.wikipedia.org/wiki/Edward_O._Thorp#Stock_market
|
| So it seems he was full of shit right? He was saying what he
| needed to say to get investors and when those investors fell
| for it he did not deliver.
|
| Sold a lot of books though...
| DistractionRect wrote:
| It reads to me like he had he simple (relative to today)
| investment strategies which where profitable, and closed shop
| when those market inefficiencies started running dry.
| skippyboxedhero wrote:
| He was also, at that point, very old. He started his first
| fund in 1968. It tells you something about the modern world
| that you can your fund successfully for three decades,
| accumulate one of the best all-time records, and you will
| still have people online call you useless if you bow out in
| your 70s when your returns go dry for a couple of years.
| skippyboxedhero wrote:
| No, not full of shit. One of the most well-known investors in
| the world, worth $1bn, and he wrote papers on sports betting
| as well.
|
| All of the things he mentions are massive problems with
| making money from gambling. All of the large gamblers in the
| US use beards, it is time-consuming and you are generally
| dealing with gambling addicts who are unreliable. The
| situation in HK was unique (and the people Benter partnered
| with proved to be very unreliable anyway when they began
| making large amounts of money).
| IncreasePosts wrote:
| His first hedge fund ran for 20 years, and then his second
| one 8 years, during which he had very positive returns, but
| the strategy he used stopped working in 2002 (probably
| because everyone else jumped on it too).
| steeeeeve wrote:
| If you have an algorithmic edge, eventually it will stop
| working. If it's a really good one, your trades become
| someone else's edge. The market is constantly changing and
| active traders are constantly looking at what's going on
| and trying to take advantage. The more I looked into
| trading, the more it was just a sea of "Use these charts",
| "don't really trust these charts", and "once you lose a ton
| of money, you'll get a feel for things"
| pixl97 wrote:
| The market is the
| https://en.wikipedia.org/wiki/Red_Queen_hypothesis in
| action.
|
| You have the market itself which is like the environment,
| it can go hot or cold based on broad trends, and if
| that's all their was fundamentals would likely work well.
|
| The problem is there the dumb prey you feed on may adapt
| and remove your niche you fit in. Even worse is there is
| no shortage of predators watching you and waiting for you
| to make a mistake and they'll eat you alive.
| jeffreyrogers wrote:
| He had a sharpe ratio similar to early Rentech and used much
| less leverage. Probably would have had similar returns to
| them if if he used similar amounts of leverage. From
| interviews with him he seems extremely risk averse. Alumni of
| his fund now run one of the few firms that could be
| considered a Rentech peer.
| srean wrote:
| Your calling him out makes you look ignorant.
|
| Thorpe is a dyed in wool information theory, probability
| theory academic who happens to be a super cool hacker at
| heart *.
|
| Among his many accomplishments are, him obtaining a _more
| general version_ of Black-Scholes model, independently and
| before Black, Scholes and Mertens had derived theirs. You may
| recall that got them the Nobel prize.
|
| Managing money and breaking Las Vegas casinos were one of
| his, side, and mostly academic, entertainments.
|
| There is a nice story of him visiting Shannon to discuss an
| information theory research paper that he, Thorpe, was
| writing. The meeting had taken a lot effort to schedule --
| Shannon was a busy man, already a celebrity. But then they
| ended up over-extending their scheduled meeting, discussing,
| brainstorming with playful eagerness, different mathematical
| methods to break several popular gambling games, starting
| with Blackjack. Turns out Shannon was a sucker for such
| entertaining hacks. (This would be one of the first
| formulations of card counting [0]) Thorpe and his students
| would then try these out in Vegas.
|
| *Taking things apart logically, to probe where things break,
| to understand how they work, that's as quintessentially an
| exercise in hacking as you can get.
|
| Prof Thorpe wrote about and proved his strategies along with
| characterizing the assumptions under which they would and had
| worked.
|
| Finally, you are you and then there is Prof. Thorpe.
|
| [0]https://en.wikipedia.org/wiki/Card_counting#History
| lordnacho wrote:
| There's a story about him buying one of the very first
| available transistors in the late 1950s in order to predict
| roulette outcomes.
| srean wrote:
| Yes. His autobiography is such an interesting read. Gives
| us a glimpse into how it was to grow up during the great
| depression.
| lordnacho wrote:
| One thing I took note of was that he was a chemistry nerd
| in school.
|
| It seems like the subject of nerd culture changed from
| waaay back when he was a kid being chemistry (you could
| make bombs), to electronics such as radio (you could do
| ham radio), to computers and then programming (video
| games).
|
| Nowadays you won't find anyone who can tell you how
| chemistry works, and a few old guys will tell you how to
| solder your own electronics, but everyone will be able to
| tell you how to code a website.
| srean wrote:
| Good observations on shifting nerdismo.
|
| On the otherhand, how can one not yield to the temptation
| of synthesizing some harmless nitrocellulose in the
| chemistry lab, or some flash powder.
|
| "Experimenting" with the flash powder set my socks on
| fire while I was temporarily blinded. I was not expecting
| that. Fun times.
| AnotherGoodName wrote:
| One thing that i don't see in automated horse betting is the work
| to look at the horses before the race.
|
| You can get a sense of a horses energy and condition on the day
| (it can be different on different days). Horse racing even has a
| parade ring before the race for this reason. I don't gamble but
| i'm absolutely sure there's signal there in visually looking at
| the horse on the day that these systems don't take into account.
|
| I wouldn't at all be surprised if a system could be far more
| successful by using vision of the parade ring (whether machine
| vision or expert human) as additional signal.
|
| In fact given my experience with horses (grew up on a farm) and
| knowing the day to day differences i'd be surprised if any pure
| algorithmic system could beat the marker without the above since
| those who do bet on horses absolutely use this signal.
| callamdelaney wrote:
| I think that that is likely a low confidence indicator,
| extremely subjective and hard to measure.
| blindriver wrote:
| The point is that it doesn't matter.
| jeffreyrogers wrote:
| Benter allegedly did use something like this in his later
| models so it probably does matter.
| beepbopboopp wrote:
| You should go look at Nikola Jokic and Russell Westbrook before
| a game and see if you can guess which player has won 2/3 of the
| most recent MVP awards, both in pregame energy and physiognomy.
|
| Winners in almost all sports mostly dont present the same.
| lordnacho wrote:
| Anecdote from the trading floor.
|
| I used to sit on a trading desk, the kind with loads of guys
| sitting next to each other and about 8 screens each. Lots of
| noise, except when it got quiet. When it did get quiet, someone
| would shout down the squawk box that they had "heard from the
| stable boys" about some horse that was on form.
|
| You couldn't not bet on this horse. Everyone did it, and
| everyone got fleeced, every time.
|
| One day, my boss decides he's had enough of this crap, and he
| goes "no, I ain't doing it, I lose my lunch money every fkn
| time, screw this".
|
| Horse comes in at 30-1, everyone is paying him a visit asking
| about what champagne to buy that day.
| PaulHoule wrote:
| I play the Dr. Z system [1] by the seat of my pants when I go to
| the track (got family who are always inviting me to the racino.)
|
| The basic idea is that more people are in the win pool so the
| odds to win are more accurate (as a probability estimator) than
| the odds to place and show (finishing second and third.) If you
| compute probability estimates for place and show based on the win
| probabilities you sometimes find that place or show are underbet
| on the favorites. Maybe one to three races a day have a good
| betting opportunity.
|
| Dr. Z's books have a number of tables for what you should do
| heuristically that he got from doing simulations. I have a Python
| script that simulates all race outcomes and points out good
| opportunities that I've been thinking of recoding for my HP Alpha
| calculator. Practically I will do a hand-waving calculation based
| on the ratio of the win to place and show odds for the favorite
| and just bet that way.
|
| Th trouble with it is you only get to bet a few times a day and
| most people want more action that that. You tend to win most of
| the time because you are betting on the favorite [2] and
| (roughly) you have three times as many ways to win betting the
| favorite to show than you do the win. You don't win very much
| when you win, however, so just a few losses can eat up what you
| win.
|
| You can't really make a living this way and I think if you've got
| the grindset to do this one seriously you can apply the same
| skills and attitude to currency options or something like that
| and make a lot more money.
|
| [1] https://www.barnesandnoble.com/w/dr-zs-beat-the-racetrack-
| wi...
|
| [2] actually the favorite is underbet so it would be a winning
| strategy to always bet on the favorite if it wasn't for the track
| taking a cut
| farceSpherule wrote:
| You can make money on horses if you know what you are doing. You
| have to have a betting strategy and have to stick to the
| strategy.
|
| You go to the track with $X and your strategy. When you are done,
| you leave. You do not stay and keep betting with your winnings.
| farceSpherule wrote:
| Down vote me all you want. You all can piss off.
|
| One of my family members - a successful General Dynamics mid-
| level exec - made a business out of horse racing and his
| handicapping strategy.
|
| He set up an LLC, paid a software engineer to, at that time,
| write a software program that would download horse and track
| stats from all of the available sources. The software would
| also ask for betting and other strategies from my family
| member.
|
| He would go to the track, bet his strategy, and leave.
|
| He easily made ~$100,000 a year from this venture. He also took
| full advantage of the the tax benefits because he made it look
| and act like a business.
| jeffreyrogers wrote:
| Algorithmic betting is widespread in horse racing now. I can't
| remember the exact figures but I think it's estimated to be about
| 40% of the total handle. There is a company that will allow
| individuals to connect directly to the betting pools and wager
| automatically. It's rumored that the biggest two bettors are
| betting over $1bn a year (of course a lot of that is recycled
| from prior payouts).
| WalterBright wrote:
| If you bet on horses, you are betting against the tide (the house
| cut). If you bet on stocks, you are betting with the tide (a
| growing economy).
|
| I prefer the latter.
| srean wrote:
| Are their big barriers to entry to become a booky ?
|
| One would assume it would be quite attractive to become one if
| he enjoys gambling. One gets to participate in the action and
| make money no matter which horse wins -- as long as they manage
| the edge right.
| gkilmain wrote:
| The biggest barrier is finding customers.
| nssnsjsjsjs wrote:
| Do you mean the person at the tracks taking odds or a
| business doing online bookmaking.
|
| Being a bookie would be fun if you like maths, are street
| smart, somewhat not highly ethical but you are disciplined
| and can control your emotions. Similar to poker I guess. And
| are knowledgeable about the sport with respect to odds not
| trivia.
|
| I doubt a typical gambler would enjoy it. Does a "foodie"
| love working in a lab testing flour samples?
| nssnsjsjsjs wrote:
| Absolutely but there are smart people in horses with enough of
| an edge to hire staff in the dozens, and those staff be at the
| higher end of office setup, perks, socials etc.
___________________________________________________________________
(page generated 2025-05-27 23:00 UTC)