Neural Ratings

[Chinbok]

Hi,<O =""></O>

I found this site recently and been reading the old posts. A lot of useful information there.<O =""></O>

I’m interested in systems using the neural ratings from AAP R&S. I’ve been recording these ratings for over 14months now as well as the information on the Unitab website, prices, unitab rating, last 3 starts, etc. I’ve developed several systems based on this and was wondering if others are doing something similar.<O =""></O>

Rather than giving each criteria a weighting and summing them, I’ve recorded each value (normalised to 100) and the horse’s ranking for each criteria. This enables me to have a rule like, ‘Top 4 in the Current Form Score with a value > 75’, for example.<O =""></O>

I normalised them to 100 as there is sometimes great variation from one criteria to another, particularly with the Time rating.<O =""></O>

If anyone is familiar with these ratings, the prizemoney and career performance ratings are the best indicators of where the winners come from.<O =""></O>

I’ve got about 10 different systems that have made a good profit in the 6 months that I’ve been betting them. (Unfortunately, I’ve also been betting unproven systems at the same time which have made a loss and seen the balance pretty much the same now as it was 6 months ago after turning over about $100k.)<O =""></O>

Here is a very simple system:<O =""></O>

Metropolitan venues only<O =""></O>
Distance = 1200m<O =""></O>
Highest Time Rater (ignore race if 2 or more = top rater)<O =""></O>
<3 first starters<O =""></O>
<4 first up (first uppers don’t have a Time rating)<O =""></O>

Has a 20% SR from over 700 bets and 12% pot (Unitab div). Would be > 20% with best tote.<O =""></O>

I would be happy to run any other set of rules if you would like or just hear from anyone using the neurals on a regular basis.<O =""></O>

Cheers<O =""></O>

[Dirk Gently]

Getting back to the use of neurals, I've always put emphasis on the JT rating. How does it correlate to winners? I have generally ignored the timeform rating as it has a very high variance, particularly on weekdays but maybe I'm missing something. Cheers.

[Chinbok]

Hi Dirk,

Personally, I don't really use JT at all. However, nearly all of my systems need both the jockey and trainer scores to be highest or 90% of the highest. This usually results iin the selections being in the top 3 or 4 in the market. So I need a SR of 40-50% to make it profitable.

I normalised each score to 100 before I store it in the database to make it easier to build systems around. Unfortunately, this means I can't use the DLR value to find out the days since last run as it is a direct correlation. EG a score of 30 (with weighting of 5) means it's last run was 9-10 days ago.

Your right about the Time value. I think it is only useful at a certain distance range.

Cheers

[wesmip1]

Chinbok,

I have found setting the following values has been ok during the week.

Trainer set to 3.
Current Form set to 3.
Prize Money set to 5.
Wet Track rating set to 0
DLR set to 0
JT set to 0
All the rest set to 1.

It doesn't work well on Saturdays. Essentially it is looking for good trainers that have a horse who has won good prizemoney and is in form.

Current Form can sometimes skew the figures as it is like the time value and doesn't always come out worthwhile. But I found leaving it off produced a worse result.

Can you run a test for above or if thats too hard can you check out horse must be in top 2 trainers, top 2 prize Money and current form in top 2.

Thanks

[Chinbok]

Hi Wesmip,

I can't remeber why but I didn't include JA, TA and JT ranking, only the score. So I've used a TA score of 90 for your test.

I've also excluded 2yo and races with >6 first starters. Too many unknowns.

In addition to these, are rules are top 2 prizemoney and top 2 current form.
Past 14 months or so:

All days:
3524 bets
1056 wins
SR 30%
Pot -10.7%

Excl Sat:
2690 bets
808 wins
SR 30%
Pot -10.2%

Appears to be no different on Saturdays. In fact Wednesdays were worst, SR 25%. Other days from 28-32% SR.

Pot (loss) figures are based on Unitab divs. Best tote would give around a 10% better return on average. Which takes it close to break even. Pretty good for this many bets.

Really needs more filters. I usually exclude fillies, fillies and mares, and mares races as they usually underperform. Over the 7 days, selections in these races performed:
Bets 411
Wins 101
SR 24.6
Pot -28.4

Still needs more work though.

Cheers

[wesmip1]

Chinbok,

Hmm, thanks for doing that . I guess I don't usually bet every race with it and I am much more selective. I usually use this as a guide to the top 2-3 horses to look at. But its good to see some figures, at least it had a strike rate of 30% too bad about the POT.

If I think of anything else I will let you know.

[Sportz]

I usually exclude fillies, fillies and mares, and mares races as they usually underperform.

Do you have any figures on what type of race work BEST?

[wesmip1]

Chinbok,

Can you email me at aussiestable@yahoo.com.au

I have another test which I was thinking about but I haven't done any preliminary testing.

Try top 2 prize money and top ranked for distance as per AAP Neurals. The distance should be distance >= 1600m.
Can you also excluded 2yo and races with >3 first starters.

I am looking for horses that run well over the longer distance (thus top rated) and are a higher class (based on prize money)

If possible can you do this for fields of less than 14 horses.

As I haven't done any testing at all this might just bomb badly....

Thanks

[Chinbok]

Hi,

The following rules:
Top 2 $, Top ranked Dist, No 2yo, <4 1st starters, dist >=1600, field size <14, produced:
Bets 2476
Wins 529
SR 21.4%
Pot -12.4%

Needs more.

[Chinbok]

Sportz,

Don't really know what race types work best.

I exclude 2yo races becuase early in the season there are alot of first starters and late in the season everyone is on them so you need a very good SR.

Always exclude fillies - too inconsistent. I've heard this from other ratings providers as well. Sometimes F&M and Mares.

I don't like to base systems on different classes. I think if it's a good system it should work just as well on maidens/class 1's as group races.

Always exclude jumps races.

I suppose the remainder are what work best for me.

Cheers

BTW, how do you quote part of another post?

[wesmip1]

Chinbok,

I see you said Career Performance and Prize Money are the best ratings out of the list for selecting winners.

What results do you get if the horse in in top 2 career Performance and top 2 prize money ? Or even top 1 Career Performance and top 1 Prize Money ?

I assume this would improve on just top 1 career perf or just top 1 Prize money.

Thanks

[crash]

"What results do you get if the horse in in top 2 career Performance and top 2 prize money ? Or even top 1 Career Performance and top 1 Prize Money ?"

A very short priced favorite:-)

[Dirk Gently]

I guess why I give a 5 to the JT is that is a factor that is not readily available unless you are using neurals. I've been using them with some success but I don't bet on slow/heavy tracks, maidens, 2yo or 3yo until after Xmas and I don't bet unless the price is atleast $4 for the win and them bet for the place. Any idea how the "$" figure is calculated?
If you want to quote a part of a post just click the quote buton on that post.
Cheers, Dirk

[moeee]

Now look here!
You are pretty much going to get a minus 10% loss because you are landing on selections that are averaging that amount under the odds.
If you want to improve your POT,you need to get some sort of minimum price acceptable for your selections.
I know all the stuff,only it don't work for me because I am a gamblerholic and deserve to lose.
Plus I got bad luck.I fell on my head at 4 years of age.

[kenchar]

Moeee,

My most humble apologies for the post I wrote about your flat head.
I felt that guilty I deleted it.

Again so sorry.

[Dirk Gently]

Hey Moeee, We still haven't had that Saturday-showdown punting challenge!
Good to see you're still roaming wild and haven't been got at by the G.A death squads!

[Chinbok]

Chinbok,

I see you said Career Performance and Prize Money are the best ratings out of the list for selecting winners.

What results do you get if the horse in in top 2 career Performance and top 2 prize money ? Or even top 1 Career Performance and top 1 Prize Money ?

I assume this would improve on just top 1 career perf or just top 1 Prize money.

Thanks
Hi Wesmip,

Excl 2yo, fillies, and races with >3 1st starters gives:

Top 2 CP, Top 2 $
Bets 17414
Wins 4231
SR 24.3%
Pot -11.4%

Top 1 CP, Top 1 $
Bets 6180
Wins 1745
SR 28.2%
Pot - 13.5%

If you added Top Jockey and Crs rating
Bets 488
Wins 197
SR 40%
Pot 3%

This is a more realistic number of bets over this time frame and is similar to a system I'm using now. If you're betting favourites (which top CP and top $ will do) you need a good SR.

Cheers

[Chinbok]

I guess why I give a 5 to the JT is that is a factor that is not readily available unless you are using neurals. I've been using them with some success but I don't bet on slow/heavy tracks, maidens, 2yo or 3yo until after Xmas and I don't bet unless the price is atleast $4 for the win and them bet for the place. Any idea how the "$" figure is calculated?
If you want to quote a part of a post just click the quote buton on that post.
Cheers, Dirk
Hi Dirk,

I've never looked into the $ figure - I assumed it was a derivation of API or total prizemoney earnt.

On the analysis I've done, I can't see any degradation in results on wet tracks. Sometimes they even perform better. None of my systems take into account the track condition or the WT rating. This may be a bad thing long term???

Cheers

[moeee]

THAT NEURAL PROGRAM LOOKS LIKE THE POT OF GOLD I WAS LOOKING FOR.
HOW COME EVERYBODY ISN'T MILLIONAIRES BY USING IT?

[Sportz]

Metropolitan venues only<O =""></O>
Distance = 1200m<O =""></O>
Highest Time Rater (ignore race if 2 or more = top rater)<O =""></O>
<3 first starters<O =""></O>
<4 first up (first uppers don’t have a Time rating)<O =""></O>

Has a 20% SR from over 700 bets and 12% pot (Unitab div). Would be > 20% with best tote.<O =""></O>


Do you count Ipswich as a metropolitan track??? If so, then R7-6 looks like a selection there tomorrow.

If not, then I guess these are the only selections for tomorrow:
Cant R2-5
Cant R6-2
Ascot R7-5

Is that right???

[Chinbok]

Do you count Ipswich as a metropolitan track??? If so, then R7-6 looks like a selection there tomorrow.

If not, then I guess these are the only selections for tomorrow:
Cant R2-5
Cant R6-2
Ascot R7-5

Is that right??? I class Ipswich as a provincial track.

I don't bet in Fillies only races so won't be on Cant R2-5. Ascot R7-5 and Cant R6-2 are qualifiers.

[Sportz]

I don't bet in Fillies only races so won't be on Cant R2-5.

It's scratched anyway.

Do you have any minimum or maximum number of starters?

[Chinbok]

I don't actually use this system as I don't have the patience for a 20% SR. If I was I would use a field size of 5 to 16. Field sizes outside of this range have made a loss but there have only been < 10 races in total so probably too small a sample.

[Spazattack]

:) Getting back to the use of neurals, I've always put emphasis on the JT rating. How does it correlate to winners? I have generally ignored the timeform rating as it has a very high variance, particularly on weekdays but maybe I'm missing something. Cheers.
I am not a big fan of JT. JA is the best influence of JA, JT and TA.
TIM is as right as it is wrong.

Here are five neural settings to mess about with:

CP2, JA1, TA1, CRS2, DIS1, $2

CP3, CF1, JA3, TA1, DIS1

JA2, CRS2, $2

CP1, CF1, JA1, BP1, DIS1, $1

JA2, JT1, $1

The first mentioned setting is by far the most consistent I have ever come across. Plenty of winners in the top two or three, particularly in the bush.

The two settings which begin with JA, come up with some great winners from time to time.

However you use the neurals, there is still work to be done beyond coming up with a selection order.

For instance, take the top two from either setting (1) or (2). Of the top two selections, by taking the top mentioned runner from either of the JA settings,will improve the win strike rate.