TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

A Gambler Who Cracked the Horse-Racing Code (2018)

187 pointsby mrbbkabout 4 years ago

9 comments

kqrabout 4 years ago
The insight about starting from the public odds is so important. It&#x27;s like running from a polar bear: you don&#x27;t have to outrun the bear, only your buddy. Not counting the track take, any deviation from the public odds in the correct direction makes you money.<p>(And the public is often reliably biased -- this is why they say sports betting is more about betting on gamblers than on games.)<p>A smaller deviation makes you less money that one time, of course, but it also saves you lots of money if you&#x27;re wrong, ensuring you live to bet another day.<p>Also in real life: people in aggregate aren&#x27;t dumb (just a bit biased), so using the public opinion as your prior and then adjusting it Bayesically with private information gets you a more reliable edge than guessing wildly.
评论 #27014996 未加载
评论 #27015149 未加载
评论 #27015938 未加载
评论 #27018719 未加载
评论 #27015684 未加载
teddykokerabout 4 years ago
You can find Benter’s paper about the model here: <a href="https:&#x2F;&#x2F;www.gwern.net&#x2F;docs&#x2F;statistics&#x2F;decision&#x2F;1994-benter.pdf" rel="nofollow">https:&#x2F;&#x2F;www.gwern.net&#x2F;docs&#x2F;statistics&#x2F;decision&#x2F;1994-benter.p...</a><p>About a year ago I read this and attempted to build a similar model (with more layers ;)) using data I scraped from Hong Kong Jockey Club’s website. Although I used much fewer features, it still produced profit in held-out races: <a href="https:&#x2F;&#x2F;teddykoker.com&#x2F;2019&#x2F;12&#x2F;beating-the-odds-machine-learning-for-horse-racing&#x2F;" rel="nofollow">https:&#x2F;&#x2F;teddykoker.com&#x2F;2019&#x2F;12&#x2F;beating-the-odds-machine-lear...</a>. Obviously there are many caveats when backtesting like this but I thought it was a fun project!
评论 #27016350 未加载
dougbabout 4 years ago
His company is <a href="http:&#x2F;&#x2F;www.ave4.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.ave4.com&#x2F;</a> I meet him a few times, interviewed to work there (didn&#x27;t get the job.) I mostly talked to a lawyer who was very nice, but reminded me of Kobayashi from the Usual Suspects. The offices are a bit extravagant with some amazing original artwork on the walls, <a href="https:&#x2F;&#x2F;www.jendoco.com&#x2F;portfolio&#x2F;fourth-avenue-analytics&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.jendoco.com&#x2F;portfolio&#x2F;fourth-avenue-analytics&#x2F;</a><p>Pre covid he hosted meetups with Pittsburgh&#x27;s R Users Group, <a href="https:&#x2F;&#x2F;www.meetup.com&#x2F;Pittsburgh-useR-Group&#x2F;events&#x2F;260701660&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.meetup.com&#x2F;Pittsburgh-useR-Group&#x2F;events&#x2F;26070166...</a><p>He is also mentioned in <a href="http:&#x2F;&#x2F;www.fortunesformula.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.fortunesformula.com&#x2F;</a> which I really enjoyed.
评论 #27017384 未加载
fighterpilotabout 4 years ago
If I remember properly: lots of proprietary data that was painstakingly assembled, and quite simple models on that data.
评论 #27014654 未加载
magicroot75about 4 years ago
Is there a book on this guy? Fascinating stuff and I&#x27;d love to dig deeper.
评论 #27014885 未加载
hamhamedabout 4 years ago
I&#x27;ve been spending almost every weekend for the past few months trying to break a crypto crash game (called bustabit) using ML. While I&#x27;m also dealing with probabilities, my challenge has to do with the limited data I&#x27;m dealt with even though their API is public.<p>In horse racing, you have access to so much shit that you can feed into the AI, like rider statistics, horse performance, horse attributes, etc. In my case, I only have the game&#x2F;round number and the bust result (red or green). From thereon, I have to create many other variables (aka featuring engineering) like round win&#x2F;lose streaks, moving averages, MACD, etc. I can also feed in what and if other players are currently betting for the round or not.<p>Currently, the house always wins. And their game is rigged so they have that 1% advantage over you. However, so far with my AI, I&#x27;ve came with enough confidence score to win as long as my bot plays 0.001% of the games.. which isn&#x27;t declared victory since those blackswan games happen once every 3 weeks.<p>There&#x27;s also another way to beat it without using any ML, just plain old fibbonaci martingale - requires around 10k starting money for error margin but it ends up always ahead of the house.. That&#x27;s just a math way to beat it and not very fun :)<p>It&#x27;s probably crazy of me to even attempt to predict randomness, but there&#x27;s something intriguing when you mix big data and ML with forced randomness. Again, they have to keep forcing the odds to be 49% vs 51%..
评论 #27014976 未加载
评论 #27020388 未加载
swader999about 4 years ago
This didn&#x27;t read like gambling, just a lot of work.
评论 #27015641 未加载
评论 #27015226 未加载
sokoloffabout 4 years ago
I don’t get why they felt like they couldn’t cash the winning bet. They paid the money and placed the bet; might as well take the win.
评论 #27016139 未加载
评论 #27016307 未加载
sneakabout 4 years ago
&gt; <i>“F---,” Benter said. “We hit it.”</i><p>Pretty sure he didn&#x27;t say &quot;F---&quot;. Why the fuck is bloomberg misquoting this guy? Why publish a quote you&#x27;re just going to censor?
评论 #27014613 未加载
评论 #27020263 未加载