I Built a Sports Betting Bot with OddsJam and ChatGPT
Вставка
- Опубліковано 15 тра 2023
- I Gave $1000 to my Sports Betting Bot powered by OddsJam, use code SIRAJ20 to get 20% off your subscription using the link below: oddsjam.com/?ref=ntjlnwv . First, a disclaimer - Do NOT invest any money in any type of trading bot or algorithmic engine that you are not willing to lose. I gave this trading bot $1000 because I was willing to lose $1000 to make a great video for my AI Wizards out there. This tutorial uses NodeJS to build a web app, MongoDB to store the data, OpenAI to create a natural language interface to data, SNScrape to pull Twitter data for free, OddsJam for +EV sports bet data, Puppeteer to scrape data, StatHead for historical sports data, ChatGPT & Bing for building an MVP.
Please Subscribe! That's what keeps me going.
Code for this video:
1. Twitter Scraping + Sentiment: colab.research.google.com/dri...
2. ChatGPT Clone:
github.com/danny-avila/chatgp...
3. OddsJam scraping code:
gist.github.com/llSourcell/ef...
4. Stathead scraping code:
github.com/gszwabowski/MLB-St...
Want more AI/ML education? Connect with me here:
Twitter: / sirajraval
Instagram: / sirajraval
Facebook: / sirajology
Linkedin: / sirajraval
I Built another Sports Betting Bot with ChatGPT:
• I Built a Sports Betti...
I Built a Trading Bot with ChatGPT:
• I Built a Trading Bot ...
I Built a Trading Bot with Bing and ChatGPT:
• I Built a Trading Bot ...
Watch ChatGPT Build an AI Startup:
• Watch ChatGPT Build an...
Watch ChatGPT Build a Finance Startup:
• Watch ChatGPT Build a ...
Learn Machine Learning in 3 Months:
• Learn Machine Learning...
Join the discord:
/ discord Join my AI community: chatgptschool.io/ Sign up for my AI Sports betting Bot, WagerGPT! (500 spots available):
www.wagergpt.co
Literally GPTesus and thank you for continuing making these videos. I talk to ChatGPT way too much now 😂
Hi Siraj. Nice content. But is hard to replicate your steps and connect pieces together. Would be much valuable if you show how all of these different scripts works together to accomplish your task.
I am not sure how sentiment analysis could be used to predict outcome. Since all the "positive" tweets only means there are lots of supporter of the chosen team. Nothing more.
True, I also think its somewhat pointless. There's no way a bot can fully filter biased tweets.
True artificial intelligence is based on gauging mass sentiment on specific sporting events. However large numbers of people feel about a game is the strongest AI of all.
@@biblicalfitness1838 yeah but Chelsea will for sure have much more supporters than Nothingham Forrest.
it's not a particularly good bot for betting, this kind of method would work better for stock picking and identifying breakouts
but you can weigh the public sentiment for both sides by amount of people, so you're not giving unfair advantage by number of supporters, but instead use percentage of supporters that think team will do well 👍
Hi Siraj , I like you video , I just wondering Do you use the chatGPT-4 instead of chatGPT ? thanks
Hi Siraj, does your WagerGPT product use and take advantage of the oddsjam API? Or are you presenting a totally separate and different concept for another betting bot version here?
Hey Siraj.....How do you do this on Windows? I've been trying for about an hour to do the steps you've shared and shown. I'm on windows and when I try to open my zip folders; they open with an error. I have no idea how to do this on Windows. Any guidance will be greatly appreciated. Thanks.
I use legs for walking, stock traders use similar tools trying to beat the marker, not often succeeding.
Thanks for your amazing work❤
Nice to see you after long time.🙏🏼👍👍
Is a monthly subscription required to have access to OddsJam?
Hi Siraj, I am stoked about this bot! I am searching your name on youtube nearly every day to check if you've uploaded anything new on this! I'm curious about how this will go. I am inspired by this series and want to make a bot for myself to connect with a mobile app to send notifications each morning.
Can you make these videos a bit longer and go deeper into implementation detail?
Thanks will do
Great comment! He has great info it’s just a little hard to replicate step by step instructions would be very valuable great video though!
Yes please can you dig more into this subject 👍👍👏👏
love your content. can we get an updated version of this, especially with the introduction of custom GPTs?
Thanks Mixed! I've just made my sports betting bot into an updated, live app. It's available at www.wagergpt.co. 350 spots remaining. You can use code ORIGINALWIZARD for 100% off the first month.
How do I change the data set to NBA statistics rather MLB?
I've wanted to have a locally running chatbot (on my own data and hw) for ages.. I thought it was still impossible on normal (but beefy) setup.
Since you need to use the API tokens, can you really say it's "Local"?
Honest question.. I'm hoping I'm wrong..
Very cool to see my chatGPT clone project featured here! I will add that yes, most of the functionality is API-dependent, but I'm working on integrating local, open-source LLMs, so yes, it can be completely local.
how do you use data of stathead to predict match ? this part of the content is omitted too much, people can not understand it at all
He showed you exactly how to do it. You pull up Wayne Gretzky's scoring stats and use it to predict tonight's NHL games.
siraj, 1. how to make decition by data from twitter,oddsjam,stathead 2.are you sure chat bing token can be used in chatgpt clone, it is no working for me? i can not find bing chat option in my chatgpt clone
So how much have you been winning since the 1st bet in this video? The overall win rate is the important question. Also, are you able to build this bot for just straight bets without the intention of arbing?
with value betting you can win 40% of the time but still profit. units would be a better method for "win rate"
@@PautKalun what’s unit?
@@javpot1232 ROI(Return of Investment in %) would be a better method, units doesnt say much. 1 unit profit can be 10 dollars or 1 billion dollars, and average units per bet can also be whatever.
100%. win rate is a decent measure for whatever model. But +/- units is the best measure for handicapper profitability. if i lose slightly more but place more units on my winners, then I am net positive on the $
No Apologies Siraj, I like your FRESH content. 😂❤
Shoutout to Jedimodi for the oddsjam plug. I've been enjoying both y'all channels.
Will this process work with any sports websites? I mean cricket or football specially in IPL with Indian fantasy play websites like Dream 11 etc
Lmao no it won't
Еще не смотрел, но уже поставил лайк) потому что твои видосы всегда офигенные😆
For someone that pays for Stathead Premium and ChatGPT Plus I need to figure how to incorporate this.
Has anyone else noticed a consistent theme in all the prising comments... Consistently... Wow i wish you could teach me and then what happens he opens a school to teach you. Go back 3 years and find out what happened. Do an outside search for this guy. Go find out what ithers have experienced with gpt predictive capability and see if it squares at all with what he is saying... Be careful as what sounds so good and easy. Think if it were this easy wouldnt everyone be a billionare. In fact if it worked so well why go through all the trouble of a youtube channel or even making a school... Doesnt that tell you something about what is really going on??
Nor sure if its just me, but when I went through the steps and launch. It opens up a login screen
can't Bard help on building the betting bot?
You skipped over where we plug in the mongodb and bing to the chatgpt clone... Plus skipped over creating the .env file..
.env was created
Thanks brother you are the best
Fresh content. LIKE! 👍
I must be doing something wrong, because when I try to run a query in the colab I get an "error retrieving" from Twitter.
I can't resist clicking the like button!
Hello nice video, can you make one on how to use betfair historical data to create a tennis and football trading strategy
Amazing! I wish your brain was available in pill form! 🙂 THANK YOU!!!
HOW CAN I CREAT ALGO BOT FOR AVIATOR CASINO GAME I HAVE STRETOGY JUST NEED BOT TO ACTIVE 24HRS IS THAT POSSIBL ?
Hi can you share with me your strategy?
Can you do a video on how to build sport bet ai for simulated matches
Didn’t have to go too far down the rabbit hole until i found where they wanted me to insert my credit card info 😂
TL;DR OddsJam does all the work.
the bing part with developer optioons is done off screen so i cant locate how to do that
that's in the browser, press Alt then follow the menu
Love it!!!
the collar for me doesn't work, it says there is an error
Although interesting how you use gpt to help you with programming this is not how you win with betting. If you did make a betting bot using one of the systems that guarantee a higher win rate than normal customers the betting platform would either ban you or restrict your account after a few days.
They wouldn't ban you. They would just reduce your limits. Once you reached $100,000 in winnings, they might cut you off. That's what Vegas does.
Cool idea! I tried but it seems like Twitter is blocking snscrape.
okay so I'm not the only one failing here
How I connect with Betfair hi lo card game
Can you help to start earning with betting,?
Aloha Siraj, Great video.
I tried to follow you, but you were moving too fast. Can you show the steps again and go into more detail?
Dude, you rock
This is insane cool.
I have to try something like this.
Everyone asking how to do it with a video of him showing you “how to do it”. This won’t work, because this is a shill.
Gets views and notoriety.
Where are the daily updates if this is profitable 🤔
I need a app built like this for my business, can you recommend anyone?
Could this be applied for horse racing??
No way, horsebetting in general is a crapshoot
Yo i won $300 on prize picks yesterday listening to siraj
Explain bro
Can you please make a bit morr clearful how to install this
King video.
Siraj, it's amazing. Can you try autotrading for forex too? using country to country economy analysis and predict which economy be strong and weak and predict forex pair price up or down
The "economy" is an illusion, so that would be hard to do. Then you have the Rothschilds deflating national currencies as a form of punishment for not giving them total control of countries' natural resources.
How many methods of making money exists... I didn't know about this method
Can you make an app for the AI sports bot so we can download on our mobile devices ?
Pls have you gotten replies?
Yes Johngul! It's live now, i made it available at www.wagergpt.co. 300 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
Hello everyone, I did like Siraj Raval when he was all about tech, but I don't get / understand why you would go off track. I get it, Owning a casino is like Owning a McDonald's franchise, a cash cow all the time dividends all the time
Hi there,
Could you make a betting model to bet on AU or UK or US horse racing ? (without Oddsjam as notorious value betting or arbing will eventually end up with your betting account being closed/restricted)
Woule be great to see your approach.
I think in general people would like to know how to create such a model, either for horse racing or greyhound radcing (In UK there are apprx.130 races per day !)
+1 for Aus
I've been scraping and building an sql database for all races, at all tracks, everyday... just in Australia.
Database currently has just over 45,000 different horse runs (~4,500 races) and I will be interrogating the data (using what I've pieced together from Bill Benter's talks) to try and replicate his approach. If it works, I'll let you know.
Currently, the limiting factors have been the amount of data (that was a few months ago, when the number of races I had data on was much lower)
imho greyhound racing is too corrupt to do that and horse racing is better to be traded than bet on
Like the sound of this @@jeedub6142 the issue is getting the odds from a good site, Bet365 or alike as the APIs are not easy to get hold of i think, be interested to see how you did
Can you make an app with this bot for bets
Surely, 👆drop a dm let's talk already
Your are the best
Anyway you we can talk man so I can understand more I learn a little slower than ppl n this is high tech
How can I make predictor aviator bot with chatgpt
Encontraste la manera de hacerlo?
@@user-xo5ri2ku3k no
I'm new here 🎉
i didnt get exactly why you need to go all over this process... in fact you use bing chat to tell you the odds. you dont even need to pay oddsjam. there are 1000s websites with free betting history data and odds. oddsjam subscription is useful for other things but completely useless for your example.
Then you copy chatGPT key but where do you use it? You say local bot... but DB is online, and you use bing LMA. what exactly is on your computer? The web page that connects all of these?
how twitter posts give you predictions and connect with the historical data? of course when you write a club name you will see positive emotions, you target the fan's posts. Not sure how accurate can this be.
Also... every odds with 1.10-1.20 have 80%-90% to win. You dont really need all these.
However, you lose money on the long run as you need to 6 of +1.2 to be a winner, and thats not the case. It's proven that you lose more often. So, you have to make at least 10 bets to see if that AI can actually pick constantly the x1.2 winners.
Hey mate, I'm an avid sports bettor. Did you manage to get this up and running?
лучшие заносы за сегодня) спс тебе за фан)
Phenomenal
Anyone have a copy of the working bot? Would love to use this, but im not super tech smart in terms of things like APIs, coding etc.
If you're non-technical I've just made my sports betting bot into an updated, live app. It's available at www.wagergpt.co. 350 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
seria bueno lo explicara un poco mas desglosado y me respondiera, gracias
This is a very valueable video
你是不是有很多机器人，其中一个就是给youtube上的评论点赞
Hello brother as you are forgive me if I bother you you can help me install that betting bot on my PC since I have no knowledge of programmer and I speak Spanish I translate the audio but it is very difficult for me you give me a hand thanks God bless you
Hey Jaider, It's live now, i made it available at www.wagergpt.co. 300 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
Siraj太牛逼了，怎么学会那么多知识的
都是自学的
Need one for the NFL.
Hey Brandon,I've got an NFL bot too now. It's available at www.wagergpt.co. 300 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
So could I pay a programmer to have this built?
Yup, you can pay me. It's live now, i made it available at www.wagergpt.co. 300 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
His other one last year ylu can build thru
If you bet the Kraken you lost.
kindly consider that not all of us are familiar with coding. there are some crucial steps that you are skipping that keep getting me lost. kindly explain it step by step like we were in kindergarten
AI cannot and will not predict accurate outcome of these games. It just simply doesn't have that capability. You should also know that Sportsbooks are putting out the "Odds" that has no meaning. There is no "Market" in Sports Betting lines. If you haven't figured it out, you will soon figure it or you might not.
That is the point of OddsJam. It compares market prices. You can definitely derive meaning by calculating the no-vig odds of a liquid market.
@@SportsBettingU Oddsjam is only good for entertainment information. Please, can you inform me on what's solid shape and not "Liquid"?
@@thebetunit What do you mean by solid shape vs liquid? Liquid in this context means an actively traded market with numerous independent data points
Have you found Oddsjam to be worth it's price? Why/why not?
True but not really. Not predicted rangers 6 days in a row, yesterday it predicted the Mariners…. We hit on each one so that’s 7 days of the bot giving us winning data.
Hi
Can your video in Hindi
this is a great video in the sense of showing something is possible but in the breath of actually showing people the stuff that matters this is a horrible video, you assume everyone knows the programs needed and how to navigate them without ever mentioning you use visual studio how to navigate the code properly, but first glance it seems like you click one button but thats not how it works in reality...you should add more detail to the little things in a video like this one. just my opinion
this is actually a great point. most people are non-technical, so i made it available at www.wagergpt.co. 300 spots remaining. Also you can use code ORIGINALWIZARD for 100% off the first month.
Hello everyone, Imo, as lone as anyone can achieve %600 or %1000 above retail cost never mind %10k above or better, we only require about %500 above retail to really feel comfortable, earning %2000 above retail is nice earning %10000 allows you to bank %80 of you're income if you're smart be safe everyone
Can you take me under your wing im going to graduate soon
When everyone began using ChatGPT,bard and other open source in everyday life.also using it for create apps. Your channel will become useless? 😢
NO WORKING !!! Chat gpt not give you this answer 😂
Don't take my comment negetive.
Rather than making about betting stuffs, try to make something useful for the society.
PLEASE! He's just earning afiliate money with those useless videos. None of this works because it has ZERO causality.
Artificial Intelligence will become so powerful, in the future, the sporting event will not even need to be played. Everything virtual.
Oddsjam is legit , but coffee just exposed how trash your gpt bot is. Your membership for the bot is a complete proven scam now
Link it
Professional sports bettors don't use oddsjam they use donbest PREMIUM 👌
Donbest = live lines
Oddsjam = NOT live lines
Donbest is $500 a month/ 5300 a year
Oddsjam is 💩
...OddsJam has live lines and is $200 a month...
@@SportsBettingU does oddsjam show live lines across the majority of sportsbooks with up to the second data with ZERO DELAY? doubt it.
Every group i hear about either use donbest or spankodds.
And I just checked oddsjam features they don't have that.
discord link doesn't work, google colab code link doesn't work, and oddsjam is paid
What happens to "sports betting" if "everyone" starts doing this?
The line moves tremendously whenever a "limit" bet is made, so these plays are only profitable for the first person who makes them. After that, it is a break-even proposition. After that, the same bet automatically becomes a money-losing proposition. It depends if you are the first, second, or third person to bet the team.
I have a gread Idea you could code. Here's my idea for "Offline AI DVR for UA-cam"
Have an input folder of Files to Classify by the filenames that are the title of the youtube video called Input_Folder
Have a Output_Folders directory, where the Subfolder Names under Output_Folders are the Classes to train a neural net, to specify where the files should be copied to. I already have this setup and lots of youtube videos already manually moved into the Subfolders. This could be used to train the classifier. once trained I'd like to run the classifier on each filename in Input_Folder, the classifier would tell me the folder name to copy it to (I would call it Folder_Destination).
Python would copy the file to \{Output_Folders}\{Folder_Destination. This would be an awsome little AI to organize files when you already have started the organizing. I use a nice little tool called "WinX UA-cam Downloader" to get the files I've put in a public folder named like "12"(the Date I started a new download list) as I browse UA-cam, I "Save to Playlist" and put it in "12" to put on my HD Later. WinX even puts them in a folder called "12 in this example.
Then when I'm ready to Download and organize I copy the URL of the Playlist, paste it into Winx and it gets all the video files and puts them in "12". Then there's the long process of organizing them into categories on my HD like described above, so I can view Videos by catagory at my leisure. ( I used to be Offline most of the time, there was a method to my madness to get lots of videos for watching later).
See all my Playlist names, and you can see I have a lot of interests. I keep the best videos by category on youtube playlists.
It would be so nice to have the program I described and it would be the main component in a larger program later that would be like an Offline AI DVR for UA-cam. Thanks for reading this long post, hope you whip up the code as a better programmer than me!
Hello fam. I am trying to get in touch with you through Twitter. Im interested in what you are doing.
NameError: name 'sntwitter' is not defined
Did you fix also experiences issues?