• 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

AD's daily selections

AustinDillon75

AustinDillon75

Colt
Some of you may know that I've been working away with speed ratings, ELO and other related things, and in time I will maybe take these to another more detailed thread when there is more to say but for now I'd just like to put up horses suggested by my own personal system.

I've been able to run backtesting with quite stunning results on these using a range of statistical techniques. Over a long period of time, they tend to rustle up 6 or 7 selections a day on average, but for now I'll just put in the two selections it's found today.

Yesterday I tried it and it was 2/2 with Kazar Forez (5/6) in the 1440 at Sedgefield and Argento Boy (5/2) in the 1525 at Naas. It also identified Largy Train (11/2) at Naas and it got the cross country winner at Cheltenham over the weekend as well (noting that whilst top rated, it did not suggest a bet based on available confidence).

So here you go for now, we'll keep track to odds on the HRB racecards at the point of posting, and record to both those and to SP.

1400 Hereford - Draco Malfoy (1/4) !!!!!
1730 Wolverhampton - Mighty Vega (5/1).

Imagine if my first tip on this results in a 1/4 shot being turned over in a 3 runner race. It does give a top rated for each race but I wont blind the thread with those for now.
 
Sol Ski said:
AustinDillon75 AustinDillon75 what is ELO ?
Click to expand...
en.wikipedia.org

Elo rating system - Wikipedia

en.wikipedia.org en.wikipedia.org

This is designed for 2 player games but what I do is take the races and attribute points based on how a horse does relative to expectation, if a horse wins 10 in a row it's restraining because it becomes expected to win, lose 10 in a row badly and it's rating drops less sharply etc. I'd prefer to keep the explanations to another thread and just issue the tips on here for now. Probably over the weekend I'll start another thread in ratings and utilities.
 
Last edited:
Four tips today.

15:24 Limerick - Big Dee 3/1
15:59 Limerick - Themanintheanorak 9/2
16:22 Chepstow - Barrow Hill Lad 5/1
17:30 Wolverhampton - Horwich 5/6
 
AustinDillon75 said:
Four tips today.

15:24 Limerick - Big Dee 3/1
15:59 Limerick - Themanintheanorak 9/2
16:22 Chepstow - Barrow Hill Lad 5/1
17:30 Wolverhampton - Horwich 5/6
Click to expand...

I'd be a little concerned with Horwich AustinDillon75 AustinDillon75 , that piece of form is suspect imo, probably ran to about 70 and who knows how good the Crisford horse might be ? The market should be a good guide throughout the day.
good luck with all four.
 
So Limerick was called off and we saw Barrow Hill Lad make little impact, drifting to 13/2.
The drift on Horwich goes our way, and he obliges at 13/8.

Total at 27/01/2026
Bets 4
Wins 2
SR 50%
Loss of -0.19 pts (-0.97 to advised).

A mixed start and far too early to draw proper conclusions.
 
The Real Screamer obliges at odds of 2/1.
Did that well considering there would have been a few concerns over a long layoff.

Total at 28/01/2026
Bets 5
Wins 3
SR 60%
Profit of +1.81 pts (+1.53 to advised).
ROI 36.2% (30.6% to advised).
 
A few plays today.

13:25:00 Thurles - Cowper Hall 7/4
14:13:00 Ayr - Wendigo 1/5
14:55:00 Thurles - El Cairos 1/7
16:20:00 Lingfield - Invincible Speed 5/2
16:25:00 Thurles - King In Love 4/1
 
13:25:00 Thurles - Cowper Hall 7/4 5th of 9
14:13:00 Ayr - Wendigo 1/5 WON AT 1/5
14:55:00 Thurles - El Cairos 1/7 WON AT 1/5
16:20:00 Lingfield - Invincible Speed 5/2 WON AT 5/2
16:25:00 Thurles - King In Love 4/1 5th of 10

Today
Bets 5
Wins 3
SR 60%
Profit of +0.9 pts (+0.84 to advised).
ROI 18.0% (16.8% to advised).

Total at 29/01/2026
Bets 10
Wins 6
SR 60%
Profit of +2.71 pts (+2.42 pts to advised).
ROI 27.1% (24.2% to advised).
 
For transparency, I've looked over the past 3 days at each top rated horse on the day, the strike rate and profit and loss. It's important because over a larger number of races it acts as a barometer, we want to see if the top rated resembles the backtesting and if it does it should support our confidence in the bets we are making here.

In those past 3 days, the top rated are 13/59 for a 22% strike rate and a 20% loss. That has to improve, despite the results above, and I have every confidence it will. The best winner was West To the Bridge at Chepstow on Tuesday, at 15/2.
 
14:02:00 Southwell - Twilight Madness 9/1 - 9th of 11
14:40:00 Catterick - Stick With Me Sam Evens - won at 4/7
16:00:00 Ffos Las - There Runs Mary 5/2 - 4th of 7
17:30:00 Wolverhampton - Quick Away - 15/2 - last of 10

Today
Bets 4
Wins 1
SR 25%
Profit of -2.47 pts (-2.00 to advised).
ROI -61.8% (-50.0% to advised).

Total at 29/01/2026
Bets 14
Wins 7
SR 50%
Profit of +0.27 pts (+0.42 pts to advised).
ROI 1.7% (3.0% to advised).

Suspended until further notice as concerns over the model and possible errors. Will return once fixed.
 
I've done a fair bit of work over the weekend on the model, and noticed it was not properly accounting for surface types, or race types, which were proving to corrupt the ratings. I've re-ran them again and they've performed in testing far better than before, I've also done some "walk forward" with the ELO which basically differentiates K-Scores for horses, trainers, jockeys, stallions and damstallions, and after tuning up optimises long-term strike rates. So the model will now run daily with the most up to date results.

14:12 Southwell - Tread Carefully (IRE) 2/1
14:55 Leopardstown - Romeo Coolio 1/2
15:07 Kempton - Madara (FR) 2/1
15:17 Southwell - By The Grace 7/2
19:30 Wolverhampton - Francesco Baracca 2/1

So these are the bets, so I will update the results later, but I do seperately want to keep an eye on all top rated runners to see how they are doing compared to the testing. Hopefully the model will update robustly daily to keep up, and it now takes just 5 minutes to read the day's racing rather than 15-20 that it did.

1770024580228.png
Again if I feel anything isn't working I'll have no hesitation pulling the plug again until resolved.

EDIT - Staffordshire Knot was going to be a bet but is now a non-runner. The top rated runner in that race (Leopardstown 14:25) will therefore be Son of Anarchy.
 
Last edited:
Oh no, I've got Staffordshire Knot in two of my acca's, damn, thought he had a decent chance even as top weight. Going to have to put some more acca's on now, I always try to hit 6/7 winners in the day at festivals, but never manage it.
 
rbtblb82 said:
Oh no, I've got Staffordshire Knot in two of my acca's, damn, thought he had a decent chance even as top weight. Going to have to put some more acca's on now, I always try to hit 6/7 winners in the day at festivals, but never manage it.
Click to expand...
R rbtblb82 sorry about that mate. I was really looking forward to seeing how he went, the model had a lot of confidence in him.

It prompts me to look at how it does when favouring top weights in large field graded handicaps but I suspect it will put a lot of clout on where recent form is decent. I'll keep an eye on it, and feed back.
 
You must log in or register to reply here.
Back
Top