There is currently 1 person viewing this thread.
Imagine that I have unearthed a lucrative betting system. It involves, for the sake of argument, horses priced at 10-1 in races of 8 to 15 runners.
I compare my % of winning horses to that of all 10-1 horses in these races. Naturally my winning % is higher, as that's why my system is so lucrative!
What happens though, if I compare the number of second and third places that I am getting? Should I expect those percentages to be higher too? Should they be the same as all 10-1 horses? Could they conceivably be less?
I just can't seem to get my head around this problem.
I compare my % of winning horses to that of all 10-1 horses in these races. Naturally my winning % is higher, as that's why my system is so lucrative!
What happens though, if I compare the number of second and third places that I am getting? Should I expect those percentages to be higher too? Should they be the same as all 10-1 horses? Could they conceivably be less?
I just can't seem to get my head around this problem.
sort by:
Show
per page
Replies: 13
|
By:
I'm not surprised... I can't get my head around that post
|
|
By:
Imagine that I have unearthed a lucrative betting system. It involves, for the sake of argument, horses priced at 10-1 in races of 8 to 15 runners.
I compare my % of winning horses to that of all 10-1 horses in these races. Naturally my winning % is higher, as that's why my system is so lucrative! What happens though, if I compare the number of second and third places that I am getting? Should I expect those percentages to be higher too? Should they be the same as all 10-1 horses? Could they conceivably be less? ChatGPT said: This is a sharp question, and it touches on some subtle statistical dynamics of betting systems and selection biases. Quick Summary (TL;DR): If your system identifies better-than-average 10-1 shots, then yes, your second- and third-place percentages are also likely to be higher than the baseline for all 10-1 horses. However, they could conceivably be the same or even lower in rare scenarios, depending on how the model selects horses (especially if it's optimized strictly for winners and ignores horses that tend to "place but not win"). Deeper Breakdown: |
|
By:
Deeper Breakdown:
|
|
By:
Well that helped, leif!
|
|
By:
 RegThis is a sharp question, and it touches on some subtle statistical dynamics of betting systems and selection biases. Quick Summary (TL;DR): If your system identifies better-than-average 10-1 shots, then yes, your second- and third-place percentages are also likely to be higher than the baseline for all 10-1 horses. However, they could conceivably be the same or even lower in rare scenarios, depending on how the model selects horses (especially if it's optimized strictly for winners and ignores horses that tend to "place but not win"). Deeper Breakdown: |
|
By:
Betfair doesn't like it
 |
|
By:
This is a sharp question, and it touches on some subtle statistical dynamics of betting systems and selection biases.
Quick Summary (TL;DR): If your system identifies better-than-average 10-1 shots, then yes, your second- and third-place percentages are also likely to be higher than the baseline for all 10-1 horses. However, they could conceivably be the same or even lower in rare scenarios, depending on how the model selects horses (especially if it's optimized strictly for winners and ignores horses that tend to "place but not win"). Deeper Breakdown: 1. Your Higher Win % Implies Better Selection: You're outperforming the average 10-1 shot in terms of win %. That suggests your selections are not random — you’ve identified horses that are mispriced or underbet. That in itself usually improves the chance of a place finish too — since to win, a horse usually must have had a high chance of placing as well. |
|
By:
anyway
 ask ChatGPt or one of his mates |
|
By:
I'm not one of 'his mates' but for what it's worth, in the breakdown at the bottom of the image he/she can compare the 'Win%' column with the 'Plc%(BF) column...
 |
|
By:
Interesting blobb.
Might there not be some scope here for e/w or place betting. Just a thought. Assuming that enough get placed that is. |
|
By:
The forum has been waiting 24 years for this, Oh Blobby. How do we get this so lucrative system, don't worry yourself about the places imo.
|
|
By:
I can't help with my maths can i, should have been 21 years!
 |
|
By:
The answer is, it depends.
If OP's system identifies a subset of placed horses which are more likely to win, then the number of 2nds and 3rds will fall. Two examples: one of each type. OP's system identifies horses which run faster than other horses. The number of placed horses will rise along with the number of winners. OP's system identifies horses that run fast and accelerate (show a turn of foot in racing parlance) then the number of places will fall as the number of winners rises. |