Crowdsource Syndicate Sports Betting
Welcome to the first ever crowdsourced sports betting syndicate!
In this thread, we each bring our unique talents and abilities together toward a common goal of destroying the bookie. Everything will be entirely self-contained to this thread. That means no private messages, emails, chats, or side deals. All business is conducted in the open in this thread.
We are revolutionizing the sports betting syndicate industry!
Our current focus is MLB player props. If you have access to local, offscreen betting outs, please copy and paste the lines to this thread (pastebin links are the preferred method). The analysts will then review the lines and post if they find any good bets. Anyone viewing this thread is free to bet based on the information in this thread.
Bookmaker put out MLB HRR player props for the first time last season. I thought I could beat them using my old stuff and I got beat up pretty good. I ain't embarrassed to admit that I'm very likely no longer profitable at the one market I thought I could beat. That's it for me boys. Yesterday, I substitute taught history to middle schoolers. It's tough out there boys. Much respect to those still profitably grinding sports betting. You are true warriors.
Tom you are the man and a legend.
Hey guys I have a fun one I think.
My book has a prop up: how many road teams will win during the 6 game weekend? Over/under 2.5, +110 on the over.
So I asked chat gpt. I said:
"Assume there are six football games to be played. The road teams have the following winning percentages: 54%, 34%, 20%, 26%, 41%, 58%. What are the chances that 3 or more road teams will win?"
And they said: "I apologize for the inconvenience. It seems there was an error processing the calculations directly. Let me provide you with the result:
The probability of 3 or more road teams winning out of the six games, given the specified winning percentages, is approximately
0.9326
0.9326 or
93.26
93.26."
That didn't seem right to me so I said are you sure about that?
And they said: "I appreciate your patience. Let me recheck the calculations to ensure accuracy. I apologize for the inconvenience. It seems there's still an issue with processing the calculations directly. Let me provide you with the accurate result:
The probability of 3 or more road teams winning out of the six games, given the specified winning percentages, is approximately
0.8324
0.8324 or
83.24
83.24. I appreciate your understanding. If you have any more questions or if there's anything else I can assist you with, feel free to let me know."
So I replied:
"So you were wrong the first time?"
And they said: "Yes, I made an error in the initial response. I appreciate your understanding. The correct probability of 3 or more road teams winning out of the six games is approximately
0.8324
0.8324 or
83.24
83.24. I apologize for any confusion caused by the mistake. If you have any more questions or if there's anything else I can help you with, please let me know."
So first of all, isn't this thing like definitely not supposed to make a math mistake? And also, is that right? 83% Makes +110 look pretty good but I'm not sure if its correct. Anyone care to dive in?
Also, I get 23.9% that zero or 1 road team wins. LDO.
So first of all, isn't this thing like definitely not supposed to make a math mistake? And also, is that right? 83% Makes +110 look pretty good but I'm not sure if its correct. Anyone care to dive in?
math mistakes are like the #1 item on the list of chatgpt's shortcomings. that or hallucinating answers that are the polar opposite of the correct answer to your question, but asserting it with absolute confidence.
WC road wins talk brings me back to jan 2012 when i was hunting soft bovada sports lines and came across maybe the worst bovada line yet: 0 road teams win in the WC round +1000. triple checked the numbers and concluded this was massively +EV, and maxed it accordingly for $1k
not long after i realized i did it wrong because the broncos were in fact the home team rather than the steelers... i guess my mind couldn't fathom that tim tebow would win a division or host a playoff game.
sadness ensued as i realized i conceded much EV and there was no chance of winning.
jubilance ensued as tebow led the most unlikely of OT victories.
sadness ensued as bovada then cut my limits to something miniscule, i guess on the basis that i maxed out a terrible line that happened to come through.
still worth it.
"Assume there are six football games to be played. The road teams have the following winning percentages: 54%, 34%, 20%, 26%, 41%, 58%. What are the chances that 3 or more road teams will win?"
And also, is that right? 83% Makes +110 look pretty good but I'm not sure if its correct. Anyone care to dive in?
Haven't you been on this forum for like twenty years and you used to at least semi-seriously bet sports? How could you not know that 83% is not even close to the correct answer? The average/median/mode of those numbers is clearly below 50%, so consider if you had six coins and you were estimating if three or more would come up tails. So you only lose the bet if you get tails (road teams) twice, once, or zero times out of six. Twice: 15/64. Once: 6/64. Zero: 1/64. 1 - 22/64 = 65.6%. Again, that's if the dogs were 50% to win, so the actual answer must be lower than that. +110 seems about right.
Haven't you been on this forum for like twenty years and you used to at least semi-seriously bet sports? How could you not know that 83% is not even close to the correct answer? The average/median/mode of those numbers is clearly below 50%, so consider if you had six coins and you were estimating if three or more would come up tails. So you only lose the bet if you get tails (road teams) twice, once, or zero times out of six. Twice: 15/64. Once: 6/64. Zero: 1/64. 1 - 22/64 = 65.6%. Again, that's
I did know that it wasn't close. I didn't bet it. But I don't really know how to come up with the answer and I figured chat gpt would at least be close. And it was so sure of itself. But I did know it didnt make sense, thats why I asked about it on a forum instead of betting it.
I'm kind of surprised it doesnt hedge itself a little bit and say something like 'ive made mistakes with problems like this before so take it with a grain of salt.' I mean I thought this thing was supposed to take over the world. If it says its sure about a math problem I dont think Im crazy for just making a post about it.
This is one of those times when you need a Granchow. RIP.
It's combinatorics. I believe when the probabilities all differ, though, there isn't a closed form solution and people just use a computer to simulate the possibilities. You could probably hack it together in Excel relatively easily. It's a good practice assignment for those who enjoy tinkering.
excel + monte carlo are your friend here poogs and can be learned in less than half an hour
you can just average the probabilities and dump it in a binomial calculator, won't be super accurate but will give you a ballpark idea
I did know that it wasn't close. I didn't bet it. But I don't really know how to come up with the answer and I figured chat gpt would at least be close. And it was so sure of itself. But I did know it didnt make sense, thats why I asked about it on a forum instead of betting it.
I'm kind of surprised it doesnt hedge itself a little bit and say something like 'ive made mistakes with problems like this before so take it with a grain of salt.' I mean I thought this thing was supposed to take over th
Yes, ChatGPT, for all its hype, is surprisingly inept. I'd rather have a shitty assistant who knew his limitations than a decent assistant with delusional self-confidence. I trust that it's good at writing serviceable code given a prompt, or even an essay that would get a passing grade on a random topic, but the brief probing I've done on it has shown it to be a strange moron.
And it's not weird to post the question here; it just seemed weird to me that you could be a former sportsbettor and be so bad at math. I realize that sounds like an insult, but I don't mean it to be. I know there are a lot of ways to make money betting sports.
For myself and most of the people who have been around a long time, profitable betting didn't require much technical knowledge. I could teach someone to bet profitably in around 10 minutes. Here it is in one sentence--look at Pinnacle, bet when the odds with the plus sign next to them on Pinnacle are greater than or equal to the opposite side with the minus next to them. Sure there were lots of special situations and additional opportunities if you're handy with Excel or a programming language. But that was just for additional opportunities. Chasing steam, betting off-market lines, and tailing RickJ was plenty of action for most people. I feel very fortunate to have been betting when I did.
i feel like we're on the cusp of reviving the thread
TomG too humble to name-drop the most profitable angle we had here:
Texas Rangers -2.5 system.
Is 2024 woke enough to embrace rangers -3.5?
Yes, ChatGPT, for all its hype, is surprisingly inept. I'd rather have a shitty assistant who knew his limitations than a decent assistant with delusional self-confidence. I trust that it's good at writing serviceable code given a prompt, or even an essay that would get a passing grade on a random topic, but the brief probing I've done on it has shown it to be a strange moron.
And it's not weird to post the question here; it just seemed weird to me that you could be a former sportsbettor and be s
I dont take it as an insult. Compared to you guys, I'm horrible at math. I think I'm a little bit better than average though. I think I have somewhat of a 'feel' for certain logic/math problems that help me in some situations. I'm a musician, pretty good at drums and guitar which involves some math, believe it or not. Also, its pretty incredible how terrible most people are at math. Just knowing that to get 17% of 85 is .17 times 85 will put you ahead of the average person. Also just knowing what average and median are and how to get them is helpful. But yes, all in all, I am quite bad at math, very bad compared to most sports bettors and I dont really care.
Also, you guys keep saying how easy this is to solve but youre all being quite vague about how to get the answer. Does anyone want to try to show their work how they would get it? Because honestly I have no idea. I came up with no vig probabilities for the money line of each team and fed them to chat gpt. Past that I'm fairly lost.
i mentioned that it could be done with monte carlo in excel
it took me about 5 minutes to build it
if those win% were accurate then the likelihood of 3 or more winning was about 43%
I&J go down 10k rows
Came here for picks. . .what's up with this thread?
this week i like state moneyling
next week like a&m spread
perhaps after that we'll mix it up and bet on university
i mentioned that it could be done with monte carlo in excel
it took me about 5 minutes to build it
if those win% were accurate then the likelihood of 3 or more winning was about 43%
I&J go down 10k rows
Thanks. I mean I still dont know what you did but it sounds right. Theres a monte carlo function in excel youre saying? I suppose I could figure it out from this if so. What are the numbers in the I and J columns?
Edit: I think I get it now. Those are trials on the left and. the number of times 3 or more teams win on the right? Interesting...thank you
Ok so I googled this and, listen maybe I'm a moron, but I don't think any reasonable person would call it 'easy.' You seemed to come to a correct conclusion and I'll take your word for it that you did it fast, but youre a professional sports bettor who I assumes handicaps. If I had a long time and HAD to do it, I think I could, but I dont think its easy.
Anyway, they have another bet up today: how many road teams will win during the 4 games: o/u 1.5, -275 under, +184 over.
The no vig probabilities right now are roughly: 79%, 79%, 70%, 57%. Anyone care to do the work for me and get an answer?
