A Handicappers Journey through a Random Forest and a Neural Network

[denniswilliams]

https://wardwissner.medium.com/a-han...k-3043caf6adaf

[Dave Schwartz]

Paywall.

[denniswilliams]

Originally Posted by Dave Schwartz

Paywall.

It's free. At least on my pc/phone. Click the 'x' on the right to remove the membership nonsense.



But this would be trivial for you....

[Dave Schwartz]

Originally Posted by denniswilliams

It's free. At least on my pc/phone. Click the 'x' on the right to remove the membership nonsense.

But this would be trivial for you....

Geez... how blind can I be?
LOL

Thanks.

[zerosky]

This from Quora

"You can sign up for free and immediately read as many public articles as possible.
If you want to read articles that are “behind the paywall” you are limited to only 3 a month"

I've read quite a few article there, If you are an author you can publish for free and make money via the partner programme.

As for the article itself, nothing really new there.
He's using neural networks and random forest to torture the PP's into coughing up the winner.

[Nitro]

Originally Posted by zerosky

As for the article itself, nothing really new there.
He's using neural networks and random forest to torture the PP's into coughing up the winner.

Nicely put!

There are so many flaws in this so-called “journey” that my conclusion is best summed up by this erroneous statement that’s made:
“After all, choosing a winner with no statistical guidance would be harder than picking a pig in a poke if you pardon the expression. However, I wish to note at the outset that despite the considerable statistical work which I will delve into in this article my spouse succeeds in picking winners by merely observing the horse’s rear as it is paraded in the paddock prior to the race.”

(I’m wondering if his spouse’s successful technique is the random method he referred to and compared when he suggested “The machine learning models are compared to a naïve Random selection”.
I mean how naïve could it be if she is successfully making a profit?)

When are people involved in trying to statistically analyze the profit potential in the horse racing game going to escape falling into the same basic entrapment? : That’s when they perpetually promote their solutions through the obvious and misleading use of GENERALIZED horse racing data that’s applied in their models.
.
.

[classhandicapper]

The more I think about the direction of the game, the more I think we need to focus our attention on things that are not easily converted into numbers and/or processed by computers. There's no way we are going to outthink and out-analyze computers over time. IMO we have to concentrate on areas where a human is providing subjective information to the computer. Then we at least have a chance to be better than the human providing the information.

[Dave Schwartz]

Originally Posted by classhandicapper

The more I think about the direction of the game, the more I think we need to focus our attention on things that are not easily converted into numbers and/or processed by computers. There's no way we are going to outthink and out-analyze computers over time. IMO we have to concentrate on areas where a human is providing subjective information to the computer. Then we at least have a chance to be better than the human providing the information.

Two questions:
1) Why not use computers in a better way instead of not using them at all?

2) If you believe "There's no way we are going to outthink and out-analyze computers over time," why would you think that a human's discernment would be able to outthink them?

Note that I mean no disrespect nor am I being sarcastic.






.

[classhandicapper]

Originally Posted by Dave Schwartz

Two questions:
1) Why not use computers in a better way instead of not using them at all?

2) If you believe "There's no way we are going to outthink and out-analyze computers over time," why would you think that a human's discernment would be able to outthink them?

Note that I mean no disrespect nor am I being sarcastic.

.

1. I currently use computer generated metrics and reports to help me handicap and also look through my data to learn and try to find inefficiencies. However, over the long haul, despite being a former computer programmer, I don't think I'm going to be able to use computers more effectively than teams of the most advanced computer scientists and mathematicians with far greater resources. It's unlikely I'm going to find much they also aren't going to find.

2. Just an example. A human can look at the horses in the paddock and potentially see something significant. He can then feed that information into a computer that will weigh it better than I can. However, my judgement in the paddock may be better than that other human. So I may see things he/she does not. If I do, those bits of information will never make it to the computer. That would still give an edge. The problem is there aren't many areas like that and the teams are going to employ high level staff.

[Poindexter]

Originally Posted by classhandicapper

The more I think about the direction of the game, the more I think we need to focus our attention on things that are not easily converted into numbers and/or processed by computers. There's no way we are going to outthink and out-analyze computers over time. IMO we have to concentrate on areas where a human is providing subjective information to the computer. Then we at least have a chance to be better than the human providing the information.

This I disagree with. A lot of your conclusions are based off of what rebates have done to this game and not what computers have done to this game. Faster horses beat slower horses, classier horses beat less classy horses. Now your focus definitely can be on less obvious things. But at the same time if you start ignoring the basics you will cause yourself more harm than good

Imo as a handicapper you have to play your game. If you see value take it. If you don’t, wait for the next race. Keep really good records and try to figure out where you’re competing and where you are getting crushed. Play your game the best you can. Work on ways to make your game better. Do not try to reinvent the wheel. Play for fun and play on a very comfortable bankroll. When you start winning consistently that is when you start to bet real money if you never win consistently so be it.

[Nitro]

Originally Posted by classhandicapper

The more I think about the direction of the game, the more I think we need to focus our attention on things that are not easily converted into numbers and/or processed by computers. There's no way we are going to outthink and out-analyze computers over time. IMO we have to concentrate on areas where a human is providing subjective information to the computer. Then we at least have a chance to be better than the human providing the information.

I’m not sure if I read your proposal correctly. I would think that the primary goal of any worthwhile computer program (related to the horse racing game) would be for humans to concentrate on providing OBJECTIVE information to produce OBJECTIVE results.
By providing SUBJECTIVE information you can only hope to achieve a range of probabilities that once again have to be (subjectively) interpreted and rationalized by humans or statistically analyzed to arrive at any number of possibilities of how likely certain outcomes will occur.

Originally Posted by Dave Schwartz

Two questions:
1) Why not use computers in a better way instead of not using them at all?

2) If you believe "There's no way we are going to outthink and out-analyze computers over time," why would you think that a human's discernment would be able to outthink them?.

1) I believe computers will always play an important role in better understanding of our game as long as we maintain that it’s only a game we’re playing. As multifaceted as it is, I would think that the programs used must utilize the most relevant and specific data in order to produce reasonable results.

2) Concerning “discernment”, I would question how a computer program can better perceive, recognize, and evaluate things that are not obvious or straightforward. Again, I have to bring up basic factors like overall physicality and intentions.
.
.

[Poindexter]

Originally Posted by classhandicapper

1. I currently use computer generated metrics and reports to help me handicap and also look through my data to learn and try to find inefficiencies. However, over the long haul, despite being a former computer programmer, I don't think I'm going to be able to use computers more effectively than teams of the most advanced computer scientists and mathematicians with far greater resources. It's unlikely I'm going to find much they also aren't going to find.

2. Just an example. A human can look at the horses in the paddock and potentially see something significant. He can then feed that information into a computer that will weigh it better than I can. However, my judgement in the paddock may be better than that other human. So I may see things he/she does not. If I do, those bits of information will never make it to the computer. That would still give an edge. The problem is there aren't many areas like that and the teams are going to employ high level staff.

I am very curious. I think you have been doing this computer thing for the last at least 5 years now. Is it working for you? You put a lot of work into this project. Do you feel like it is taking you somewhere? If so , where?

Personally, I am very happy with the pen and paper handicapping game. I just print out my numbers and cap away. I have zero desire to develop or analyze databases. I am not claiming to be right or wrong it just works for me.

[classhandicapper]

Originally Posted by Poindexter

This I disagree with. A lot of your conclusions are based off of what rebates have done to this game and not what computers have done to this game.

It's computer models that are making the odds more efficient, not the rebates. The rebates are just allowing the biggest teams to profit despite the odds being more efficient.

[classhandicapper]

Originally Posted by Nitro

I’m not sure if I read your proposal correctly. I would think that the primary goal of any worthwhile computer program (related to the horse racing game) would be for humans to concentrate on providing OBJECTIVE information to produce OBJECTIVE results.
By providing SUBJECTIVE information you can only hope to achieve a range of probabilities that once again have to be (subjectively) interpreted and rationalized by humans or statistically analyzed to arrive at any number of possibilities of how likely certain outcomes will occur.

.

How many lengths some trouble cost a horse is somewhat subjective.

To not include it would be a bigger mistake than including it even though it's subjective.

My view is that since another human will be making that subjective judgement, I can potentially be better than others at that kind of thing. So there's potentially still value there. There's no value if we are both using the same speed figures, finishing position, beaten lengths, trainer stats etc... because their info is as good as mine and a learning computer will do a better job than a human at weighing data like that.

[classhandicapper]

Originally Posted by Poindexter

I am very curious. I think you have been doing this computer thing for the last at least 5 years now. Is it working for you? You put a lot of work into this project. Do you feel like it is taking you somewhere? If so , where?

I'm doing it since late 2014.

I know WAY more about a lot of things now than prior to having all that data to study, but I think the game got a lot tougher over the same period. Whatever edge I still have, it's smaller now than it was in the 90s when I knew less.