|
|
02-25-2023, 03:27 PM
|
#61
|
Registered User
Join Date: Nov 2012
Posts: 1,541
|
With any computer-based approach it's only going to be as good as the inputs. If you feed AI DRF data with Beyer figures I don't know how much it can actually learn. There's a lot of relevance to who takes money too, and how does that get presented to AI. Coding for horse racing is incredibly labor intensive; just to get the data in position to be analyzed is a big effort. Then once you have said 'system' you need today's data to be crunched because it needs to look at grouped data not just raw data on a card, everything changes relevance within the group. Computers do an awfully good job if they're properly spoon fed really good inputs, but where are those inputs coming from? Beyer figures? CJ's pace figures? Raw times? My stuff? Nobody has my stuff in CSV except for me. So then they have to build something like I built or steveb's stuff and feed that 'goodness' to the AI. Otherwise it gets nothing and nowhere with just raw PPs IMO.
Last edited by MJC922; 02-25-2023 at 03:29 PM.
|
|
|
02-25-2023, 03:34 PM
|
#62
|
Buckle Up
Join Date: Apr 2014
Posts: 10,614
|
Quote:
Originally Posted by MJC922
With any computer-based approach it's only going to be as good as the inputs. If you feed AI DRF data with Beyer figures I don't know how much it can actually learn. There's a lot of relevance to who takes money too, and how does that get presented to AI. Coding for horse racing is incredibly labor intensive; just to get the data in position to be analyzed is a big effort. Then once you have said 'system' you need today's data to be crunched because it needs to look at grouped data not just raw data on a card, everything changes relevance within the group. Computers do an awfully good job if they're properly spoon fed really good inputs, but where are those inputs coming from? Beyer figures? CJ's pace figures? Raw times? My stuff? Nobody has my stuff in CSV except for me. So then they have to build something like I built or steveb's stuff and feed that 'goodness' to the AI. Otherwise it gets nothing and nowhere with just raw PPs IMO.
|
Well stated....And that's just for getting started.
|
|
|
02-25-2023, 03:57 PM
|
#63
|
PA Steward
Join Date: Mar 2001
Location: Del Boca Vista
Posts: 88,543
|
Why are you guys focusing on problems that can by EASILY overcome with the right people involved?
Obviously, you aren't going to start betting races with AI until you come up with a model that actually works.
|
|
|
02-25-2023, 04:07 PM
|
#64
|
Registered User
Join Date: Dec 2021
Posts: 2,081
|
Quote:
Originally Posted by PaceAdvantage
Why are you guys focusing on problems that can by EASILY overcome with the right people involved?
Obviously, you aren't going to start betting races with AI until you come up with a model that actually works.
|
Bingo.
AI is way beyond computer models. AI can learn on its own.
Like every CAW model ever made, they ran through a bunch of tests before unleashing it into a real environment. You'd do the same with an AI.
Where an AI is different, is that it will learn and can get it's own information and not reliant upon a human mind to program and tell it what to do. A CAW is only as good as the software running it. AI will be ever evolving and creating it's own curve way beyond anything a human mind could some up with.
Plug AI into the internet, and it can find it's own results, figure out new methods and means, and make adjustments on the fly. Even cancel and change bets based upon 'action'. An AI can learn from the crappy programming given, and make itself better on it's own.
|
|
|
02-25-2023, 04:13 PM
|
#65
|
Buckle Up
Join Date: Apr 2014
Posts: 10,614
|
Quote:
Originally Posted by PaceAdvantage
Why are you guys focusing on problems that can by EASILY overcome with the right people involved?
Obviously, you aren't going to start betting races with AI until you come up with a model that actually works.
|
Quote:
Originally Posted by PalaceOfFortLarned
Bingo.
AI is way beyond computer models. AI can learn on its own.
Like every CAW model ever made, they ran through a bunch of tests before unleashing it into a real environment. You'd do the same with an AI.
Where an AI is different, is that it will learn and can get it's own information and not reliant upon a human mind to program and tell it what to do. A CAW is only as good as the software running it. AI will be ever evolving and creating it's own curve way beyond anything a human mind could some up with.
Plug AI into the internet, and it can find it's own results, figure out new methods and means, and make adjustments on the fly. Even cancel and change bets based upon 'action'. An AI can learn from the crappy programming given, and make itself better on it's own.
|
Try finding the "right people", they're on their own.
What utter nonsense with AI versus the God given human mind....
|
|
|
02-25-2023, 04:16 PM
|
#66
|
PA Steward
Join Date: Mar 2001
Location: Del Boca Vista
Posts: 88,543
|
Quote:
Originally Posted by ReplayRandall
Try finding the "right people", they're on their own.
What utter nonsense with AI versus the God given human mind....
|
Seriously? Maybe this right here is the answer to my original question.
Well, it's only a part of the answer, with only a small part of the population involved.
Those who think like you have always been left behind.
|
|
|
02-25-2023, 04:17 PM
|
#67
|
PA Steward
Join Date: Mar 2001
Location: Del Boca Vista
Posts: 88,543
|
Quote:
Originally Posted by PalaceOfFortLarned
Bingo.
AI is way beyond computer models. AI can learn on its own.
Like every CAW model ever made, they ran through a bunch of tests before unleashing it into a real environment. You'd do the same with an AI.
Where an AI is different, is that it will learn and can get it's own information and not reliant upon a human mind to program and tell it what to do. A CAW is only as good as the software running it. AI will be ever evolving and creating it's own curve way beyond anything a human mind could some up with.
Plug AI into the internet, and it can find it's own results, figure out new methods and means, and make adjustments on the fly. Even cancel and change bets based upon 'action'. An AI can learn from the crappy programming given, and make itself better on it's own.
|
I was going to amend my last post to include part of the above.
Figuring out which inputs are best (ie. NON GARBAGE IN) can also be left up to AI to figure out.
|
|
|
02-25-2023, 04:18 PM
|
#68
|
Buckle Up
Join Date: Apr 2014
Posts: 10,614
|
Quote:
Originally Posted by PaceAdvantage
Seriously? Maybe this right here is the answer to my original question.
Well, it's only a part of the answer, with only a small part of the population involved.
Those who think like you have always been left behind.
|
Thanks for the laugh...
|
|
|
02-25-2023, 04:19 PM
|
#69
|
PA Steward
Join Date: Mar 2001
Location: Del Boca Vista
Posts: 88,543
|
Quote:
Originally Posted by ReplayRandall
Thanks for the laugh...
|
I get it...you're a big winner.
That's fine. Nobody is questioning that.
What does THAT have to do with THIS discussion?
Absolutely nothing.
|
|
|
02-25-2023, 04:22 PM
|
#70
|
Buckle Up
Join Date: Apr 2014
Posts: 10,614
|
Quote:
Originally Posted by PaceAdvantage
I get it...you're a big winner.
That's fine. Nobody is questioning that.
What does THAT have to do with THIS discussion?
Absolutely nothing.
|
You don't see the answer yet?...
It's in the thread, but you're looking for validation of what you think and believe.
|
|
|
02-25-2023, 05:08 PM
|
#71
|
The Voice of Reason!
Join Date: Mar 2001
Location: Canandaigua, New york
Posts: 112,819
|
Can you use ChatGPT? $20 a month.
__________________
Who does the Racing Form Detective like in this one?
|
|
|
02-25-2023, 05:44 PM
|
#72
|
Registered User
Join Date: Apr 2006
Posts: 278
|
Quote:
Originally Posted by MJC922
With any computer-based approach it's only going to be as good as the inputs. If you feed AI DRF data with Beyer figures I don't know how much it can actually learn. There's a lot of relevance to who takes money too, and how does that get presented to AI. Coding for horse racing is incredibly labor intensive; just to get the data in position to be analyzed is a big effort. Then once you have said 'system' you need today's data to be crunched because it needs to look at grouped data not just raw data on a card, everything changes relevance within the group. Computers do an awfully good job if they're properly spoon fed really good inputs, but where are those inputs coming from? Beyer figures? CJ's pace figures? Raw times? My stuff? Nobody has my stuff in CSV except for me. So then they have to build something like I built or steveb's stuff and feed that 'goodness' to the AI. Otherwise it gets nothing and nowhere with just raw PPs IMO.
|
This is prolly the best comment in the thread. Some of you are telling on yourselves about your own working knowledge about how “AI” works in horse racing. Might want to let an AI loose on all the posts in the history of this board and I would be happy to have my machines bet against it.
Bottom line is you will spend the majority of your time data cleaning more than any other task. If you think the data that’s freely available (or even exorbitantly priced available) and that is going to be good enough for an “AI” to bet, you are sorely misinformed.
|
|
|
02-25-2023, 05:45 PM
|
#73
|
Registered User
Join Date: Dec 2001
Location: JCapper Platinum: Kind of like Deep Blue... but for horses.
Posts: 5,287
|
If a privately funded big data AI project were turned loose on horseracing a few of its early realizations might be:
Acquiring a giant dataset might be useful.
CRW teams are the main competition.
What if the algorithm decides hacking the Equibase servers is the optimal way to acquire historical data?
What if the algorithm decides unleashing DDOS attacks through thousands of proxy servers against the servers of RGS and Elite Turf Club is a great way to reduce competition in the pools?
Who says AI has to be ethical?
Just putting that out there.
-jp
.
__________________
Team JCapper: 2011 PAIHL Regular Season ROI Leader after 15 weeks
www.JCapper.com
|
|
|
02-25-2023, 06:14 PM
|
#74
|
Registered User
Join Date: Jan 2022
Posts: 780
|
"It becomes self-aware at 2:14 a.m. Eastern time, August 29th. In a panic, they try to pull the plug. Sarah Connor : Skynet fights back."
|
|
|
02-25-2023, 06:27 PM
|
#75
|
Registered User
Join Date: Dec 2001
Location: JCapper Platinum: Kind of like Deep Blue... but for horses.
Posts: 5,287
|
Quote:
Originally Posted by o_crunk
This is prolly the best comment in the thread. Some of you are telling on yourselves about your own working knowledge about how “AI” works in horse racing. Might want to let an AI loose on all the posts in the history of this board and I would be happy to have my machines bet against it.
Bottom line is you will spend the majority of your time data cleaning more than any other task. If you think the data that’s freely available (or even exorbitantly priced available) and that is going to be good enough for an “AI” to bet, you are sorely misinformed.
|
I would agree with the bolded part. Cleaning the data prior to analysis is huge.
Not so sure about the sentence after that.
The key would be making some very astute observations about horses and races very few players have ever thought of before.
And from there creating custom features from those observations, adding those features to the data - and quietly using them.
I've personally seen it done.
Horseracing pools are different than financial markets in that the more money on a horse in the parimutuel pools the lower the payoff.
Whereas increased money flowing to the shares of XYZ Corp results in a higher share price (at least until big money cashes out.)
Also the total addressable market for horseracing software/algorithms is the tiniest imaginable fraction vs. that of currency trading (Forex), and world stock markets (NYSE, Nasdaq, S&P 500, Stoxx, etc.)
I think that's the real reason why big data innovation hasn't found its way to horse racing.
I also think both CJ and Ralph said it much better than I ever could several pages ago.
-jp
.
__________________
Team JCapper: 2011 PAIHL Regular Season ROI Leader after 15 weeks
www.JCapper.com
Last edited by Jeff P; 02-25-2023 at 06:31 PM.
|
|
|
|
|
Posting Rules
|
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
HTML code is Off
|
|
|
|
|