• Hi Guest Just in case you were not aware I wanted to highlight that you can now get a free 7 day trial of Horseracebase here.
    We have a lot of members who are existing users of Horseracebase so help is always available if needed, as well as dedicated section of the fourm here.
    Best Wishes
    AR

Can AI Find Winners in UK Flat Racing?

Chesham said:
Good luck with your AI developments cpw cpw , Mark is one of the good guys and well respected
Click to expand...
I know he is one of the good guys and respected. I didn't think the group was still going as a lot of the information on the website is very old. If it's still active I may swing by and say hello. It has been a while.
 
cpw said:
I know he is one of the good guys and respected. I didn't think the group was still going as a lot of the information on the website is very old. If it's still active I may swing by and say hello. It has been a while.
Click to expand...
I think he has a forum dedicated to AI

IMG_2235.jpeg
 
Last edited:
cpw cpw Good thread.

I've only scratched the surface using Chat gpt for excel functions/conditions in relation to compiling horse race ratings.

My approach is slow and steady as I want to ensure each piece of data is relevant to the whole rating, convert to a tissue price and compare the live market for value...etc

Some of the data sets you've posted look promising, as it gives the total ratings at the end. It's just a question of how much weighting/adjustment is made for each piece of data to obtain consistent results. That bit will take time, dependant on your own knowledge/experience.
 
cpw said:
That's my point Paul. We are thinking old school. We don't need to download any code and run. Just provide context and data and it does the rest. You simply have to ask the questions. You have an SME and Data Analyst all built in. You just ask it about the data it has in plain English :dreads:
Click to expand...
I believe that if you're using a paid sports site, the AI might not be able to access the data directly. However, you can copy and paste some of the data into the AI for analysis.

I asked AI to write me a brief history of the steel industry and IMO it saved me a lot of time. I also asked it for UK water stress summary and again great results.
Use Google Keep (when you find the right line of questioning) to save your question then you can refer back to it !
 
Paul Brown said:
I believe that if you're using a paid sports site, the AI might not be able to access the data directly. However, you can copy and paste some of the data into the AI for analysis.

I asked AI to write me a brief history of the steel industry and IMO it saved me a lot of time. I also asked it for UK water stress summary and again great results.
Use Google Keep (when you find the right line of questioning) to save your question then you can refer back to it !
Click to expand...
You may also find AI limits your data unless you go premium.
 
DuckandDive said:
cpw cpw Good thread.

I've only scratched the surface using Chat gpt for excel functions/conditions in relation to compiling horse race ratings.

My approach is slow and steady as I want to ensure each piece of data is relevant to the whole rating, convert to a tissue price and compare the live market for value...etc

Some of the data sets you've posted look promising, as it gives the total ratings at the end. It's just a question of how much weighting/adjustment is made for each piece of data to obtain consistent results. That bit will take time, dependant on your own knowledge/experience.
Click to expand...
The thing is you can get AI to do the weights for you based on historical results. No need to worry about knowledge and experience it's all about the data. The more data you have the better. I have over 30 years worth.
 
gerry said:
Would be interesting putting gentle ellen and havana pursuit as i think this one could be big danger only not my tupe of race as nothing sticks out the worries with havana are the draw the no track exsperience and i have new way of applying horses and dosnt fit it this race.
Click to expand...
So I just ask the AI to do the compare. This is what I get
When comparing Gentle Ellen and Havana Pursuit, both horses have notable differences that can help determine which is better suited for this race.

Form & Recent Performance:​

  • Gentle Ellen: Has shown mixed recent form, with her latest effort being a below-par sixth of twelve at Haydock. However, she has won three times at 6f and is proven over this course and distance. If she bounces back to form, she has potential, as her overall win rate is decent.
  • Havana Pursuit: Also out of form, with a seventh-place finish in his last run at Carlisle. He has struggled to make an impact recently, and his overall win rate is lower than Gentle Ellen's. He hasn’t placed in his last 11 runs over this distance.
Preference: Gentle Ellen gets the edge here. While both are out of form, she has a better track record at the distance and course.

Course & Distance (C&D) Experience:​

  • Gentle Ellen: Has won over both course and distance, which is a significant positive. Her 33.33% win rate at the course and the same percentage at this distance shows she’s comfortable under these conditions.
  • Havana Pursuit: Has no experience at this course and a relatively poor record over the distance (1 win from 11 attempts), making him less reliable here.
Preference: Gentle Ellen is far more reliable with her C&D-winning form.

Going & Conditions:​

  • Gentle Ellen: Has 3 wins and 4 places from 17 runs on similar going, which is a fair return. She’s proven she can handle a variety of ground conditions, from good to soft.
  • Havana Pursuit: Has 2 wins from 9 runs on similar going, which is reasonable but offers less reassurance than Ellen's form in similar conditions.
Preference: Gentle Ellen is more proven on different types of going and has more experience overall.

Distance:​

  • Gentle Ellen: Has 3 wins from 10 starts over this distance (30%), a solid strike rate for 6f races. She is proven at this trip and tends to perform well over it.
  • Havana Pursuit: Has only 1 win from 11 starts at this distance, which shows inconsistency and suggests the trip might not be ideal for him.
Preference: Gentle Ellen has a much better record over 6f, making her the safer option at this trip.

Overall Consistency:​

  • Gentle Ellen: Despite recent dips in form, her overall record suggests she is more consistent, especially at this course and distance. She has placed or won in 15% of all her flat races, a sign of steadier performance.
  • Havana Pursuit: His lack of recent placings and inconsistency over the distance make him a riskier choice. His overall performance has been patchy, and his form is unreliable.
Preference: Gentle Ellen is more consistent across various aspects, including course, distance, and going.

Conclusion & Preference:​

Gentle Ellen is the clear preference over Havana Pursuit. She has a stronger track record at both the course and distance, more experience on similar going, and a higher overall level of consistency. While both horses are coming into the race after below-par runs, Gentle Ellen has more proven ability in these conditions and is better suited for the race.

4o
 
Paul Brown said:
I believe that if you're using a paid sports site, the AI might not be able to access the data directly. However, you can copy and paste some of the data into the AI for analysis.

I asked AI to write me a brief history of the steel industry and IMO it saved me a lot of time. I also asked it for UK water stress summary and again great results.
Use Google Keep (when you find the right line of questioning) to save your question then you can refer back to it !
Click to expand...
No need for Google Keep, you can save and name and go back to the thread and build up its knowledge from there. Exciting times are ahead for AI.
 
cpw said:
The thing is you can get AI to do the weights for you based on historical results. No need to worry about knowledge and experience it's all about the data. The more data you have the better. I have over 30 years worth.
Click to expand...
How good results wise has AI been for you ? In other words how much profit points wise has your test of AI been.
 
cpw said:
No need for Google Keep, you can save and name and go back to the thread and build up its knowledge from there. Exciting times are ahead for AI.
Click to expand...
I agree you can but I always like a back up. I have about 50 queries in my AI so just in case I forget the wording of my original question I can just copy and paste from GK to AI. If I am working on multiple queries (not Horseracing) I can work through pretty fast. Be it 'the demise of Port Talbot steel works' or something else.
 
Last edited:
cpw said:
No need for Google Keep, you can save and name and go back to the thread and build up its knowledge from there. Exciting times are ahead for AI.
Click to expand...
No paid sports site. Just what is out there for FREE
 
Paul Brown said:
How good results wise has AI been for you ? In other words how much profit points wise has your test of AI been.
Click to expand...
I am still experimenting but so far so good. I am still wondering if I should be including more details on jockey and trainer stats as weights and then include this along with my other factors. The proof is in the winning right.1727094387583.png
 
Paul Brown said:
I agree you can but I always like a back up. I have about 50 queries in my AI so just in case I forget the wording of my original question I can just copy and paste from GK to AI. If I am working on multiple queries (not Horseracing) I can work through pretty fast. Be it 'the demise of Port Talbot steel works' or something else.
Click to expand...
Got it makes sense. Also if it goes down at least you still have your prompt. I use a similar approach saving to a Google Doc. You never know if they make an upgrade and you lose your prompt detail.
 
It makes you wonder why this one has been backed into Fav. Other than a link to the late Barney Curly and BHA having dropped

IMG_2240.jpeg

Purchased at the 2023 Horses in Training for a Grand

Pedigree

https://www.tattersalls.com/cat/autumnhit/2023/1535.pdf
LTO TF Comment
took a step back in the right direction from falling mark after 5 months off, not seen to best effect from an unhelpful draw/position; raced wide, mid-field, took strong hold, ridden over 1f out, kept on, not ideally placed.




What does AI mke of this one cpw cpw is it a red herring or a genuine gamble
 
Last edited:
You must log in or register to reply here.
Back
Top