Hi Andrew, I like the same columns that you do, but I also add abRX and abRy. I've been looking at them individually and doing a union as a contender selector. So my question for the group would be: if I were to build an object consisting of abPACE BH, pcrH, abRX, abRY and PEN- would that be duplicative of an object that already exists?

Jim,

I'm impressed. That's an unheard-of ROI. Good job.

My research looks at ~3,000 races, splitting them into development (where the model is created), test (seeing if the development model is for real or a fluke), and validation (seeing if the model fades after a month) data sets. I've been creating predictive models for 25 years (mostly in the medical field), and I've learned that all models definitely have a "shelf life" . This should be the case for horse racing, where tracks, purses, weather conditions, etc... change frequently,

So you may have found the golden bullet (killing off whales). But my experience tells me that most models (or at least, the ones I've created) don't persist.

I had a call with Dave yesterday to go over this. Rather than trying to decide on the factors myself-- I decided to test letting the 26,000 AI-based columns made up of 30 factors chosen by the AI engine specifically for this TYPE OF RACE (based upon how the AI sees "race type.") do the work for me. 150 factors (also known as COLUMNS) in one object.

Dirt/Tapeta races from Saturday and Monday. No Turf, no races with FTS's, no races with two d1's, two L1's or a d1/L1, or races where a H9 is the top selection.
32 races = $64.00. Return = $139.94. ROI = 118.65%. There was actually a d1 $25.00 winner that I left out since I haven't seen that high of a payoff on a d1.

You may want to look at the 26,000 columns and see how they work with your columns and also integrate with the 88% - Finding the Race Within the Race.

Perhaps with a little help from Dave or Ponyplayer I will figure out how to post a screenshot on this board and explain how simple my thought process is. — Tony Kofalt

Would love to see that, Tony. What I have done in the past is upload the screenshot to Dropbox, create a public link to it, then copy the link to the Forum message. I can help you with this if you like. Send me a private message.

As to me knowing a lot about deT, you are overestimating that ;-)

I use about 5 columns in my predictive models (different columns for the models). The best seem to be the morning line (duh), AB, the Neal, pcrH, and Rey4. Are other DET people seeing similar or different results?

Hey Tom, I'd say I use the Magnitude rating D1, m3 and H5, etc most heavily. Since committing to DET, I have modified immensely. I had done all my handicapping through the traditional racing form. I was using the same info everyone else had and I was fortunate enough to eke out a living. After seeing DET in action, I committed myself to learn all I could about DET output. Today I use only DET info. It took months of reviewing results to develop methods and build confidence. I now print out a version AI Ast displays and do all my handicapping from there. The key, I think is using data my opponents don't have. Tom I've listened to your input and I'm sure you have a better grasp on
DET than I do. Perhaps with a little help from Dave or Ponyplayer I will figure out how to post a screenshot on this board and explain how simple my thought process is.

In the most recent video, which is publicly available (for now), I showed how all handicapping basically comes down to a HANDFUL OF COLUMNS.

I asked the question, "Which columns do you have the greatest belief in?"

A couple of people asked me questions that sounded a lot like, "What are you talking about? I don't actually have ANY columns because I don't use reports."

CLARITY: WHAT'S A COLUMN?
Imagine that you have personal names for FACTORS that most of us could identify easily.
ES as running style - many use a "column" called Quirin ES Points for that, while others use the old Fred Davis approach, or some home-grown creation.

If you HAVE a "sheet" of some kind, that would be one of your columns.

As a further example, when I use the word "SPEED" I mean "speed ratings," but many people automatically connect that to "EARLY SPEED."

Doesn't really matter... I see them... whatever we call them... they are all columns in SOMEONE'S data.


CLARITY: DIFFERENCE BETWEEN COLUMNS & FACTORS
... or... When does a Single Factor become a COLUMN or vice versa?
Consider the PSR rating. (Projected Speed Rating, a proprietary HDW rating that is kin to BRIS Prime Power. (Not the same under the hood, but like the same horses very often.)

That "factor" called PSR is in our system as Factor #174 (rank for PSR). It's hit rate on rank=1 is ~31%.
(For those unaware, DET currently has about 3,200 factors for each horse.)

So, think of PSR as a COLUMN.
Thus, it can be both a COLUMN & a FACTOR.


CLARITY: HANDICAPPING OBJECTS
A Handicapping Object is a handicapping construct with up to 5 factors.
Each factor has a weight controlled by the user.

Thus:
Handicapping Object = (up to) 5 factors.

Because you can fire an OBJECT and see the results in... wait for it... a SORTABLE COLUMN...

... It can also be one of YOUR COLUMNS.

CLARITY: COLUMNS to FACTORS to OBJECTS TO COLUMNS
Imagine the PENELOPE CONSENSUS PAGE.




Each of these AI-based columns are made up of 30 factors chosen by the AI engine specifically for this TYPE OF RACE (based upon how the AI sees "race type.")
(special note: there are 40,000 race type permutations.)

Consider just the PEN column...
The ranks for that column are available as a single factor.


CLARITY: REAL POWER OBJECTS
If you considering that you can put FIVE factors into an OBJECT...


... you can effectively put 5 x 30 = 150 factors into ONE OBJECT.
Not just any factors... but the 150 factors (also known as COLUMNS) into a single object.

Next, recall that there exists a simple box that allows you to FIRE TWO OBJECTS TOGETHER AS ONE, you can actually use *300-AI-chosen factors.


SOME NOTES
*There are factors used across multiple columns.
___________________
*When you REMOVE a horse from the screen his ranks are recovered.

(This is where Brian's idea of race-within-a-race, race-within-a-race, race-within-a-race came from.)
(Otherwise known as "Search the current contenders for the 88%.)
(Quite a brilliant idea, actually.)
@ponyplayer

___________________
*Did you know that the whale teams typically use between 150 and 175 factors maximum?

Here are my guidelines. — Tony Kofalt

Great job Tony, you are an inspiration.

So how did deT figure into your process?

The majority of my plays are on horizontal bets, specifically P 3-4 and P5's. In all honesty I am far from being an expert with DET, but I have committed myself to make this my lone tool. Let me offer a few ideas on horizontal wagers that you may find helpful. All feedback is appreciated. Here are my guidelines.
01) I start by separating my contenders into two groups. A's and B's. A's include the top contenders, those most likely to win and horses where I expect their final odds to be overlaid. B's are all other contenders. A typical race for me will have one to four contenders.
02) Once I've created the two contender groups I am off to ticket writing. I will use some races at Sar today as examples. I will focus on the early P4, races 2 thru 5. The contenders are noted below by program number.
A's B's
Race 2 2,4 1,3,6
Race 3 10 1,9,11
Race 4 6,7 1,3
Race 5 4,8 1,5,14
There were 5 contenders in race 2. One of the A's won and paid $9.24 as the 2nd betting choice. No big deal but we are alive. Race 3 featured a lone A along with 3 B's. My A was beaten, fortunately one of my B's won paying $7.50. Another 2nd choice winner.
I race 4, there were 2 losing A' s with a B winning to pay $18.68. In race 5 an A delivered at $17.54. We have a winner!! To structure the tickets I required 2 A's to win. There is no magic in requiring 2 A's to win. Its my attempt to balance investment with potential profit. So the tickets looked like this.
Ticket 1- 2,4 with 10 with 6,7 with 4,8= $4.00.
Ticket 2- 2,4 with 1,9,10,11 with 1,3,6,7 with 1,4,5,8,14= $80
Ticket 3- 2,4 with 1,9,10,11 with 6,7 with 1,4,5,8,14=$40
Ticket 4- 1,3,6 with 10 with 1,3,6,7 with 1,4,5,8,14=$30
Ticket 5- 1,3,6 with 10 with 6,7 with 4,8=$6
Playing 50 cent tickets resulted with an investment of $160 cashing $1379.85 P4.

Here's a nice one in SAR1 today. First I run AI Asst using a PSR Whale-friendly type object. As Dave says-- pushes winners to the top and losers to the bottom. Then I like to check for the number of D's and L's and the "pace of the race" using pcE, pcEP, etc and es "early speed" points. There's one d1 that went off at 3/5. Not a strong front runner based on pcE and pcEP. Also, has the lowest early speed points-- 3. If this holds, then the d1 will be last and have to pass all of the other contenders. A tough assignment for a $12K claimer. I have much more confidence tossing the d1.
The #7 is a toss based on the AB. Then run the "race within the race" and the #4 jumps out as the selection. The race ran as expected with the d1 breaking last and the #4 won easily paying $7.54.

How much is your ticket at $1.00?? Would the following
help?

It seems that a much larger percentage of non-d's and L's
(profit horses) are coming in. And we are hitting a very high
number of profit horses.

If you 1x2x2x2 = $8 and do only the best d or L for the single
and do 1 single per race you, have 4 races x $8 = $32.00
if you eliminate all the d's and L's you have 2x2x2x2 = $16
on 1 ticket if it is all profit horses that win.

$32 + $16 = $48.00 would be the investment. You won't have
a huge hit rate but it should be solid and you should make money.

Another question is, what percentage of pick 4's do I need
to hit to make my psyche comfortable? The higher the percentage
of wins that you need, the greater the coverage you must have.
But, that greater coverage also means less ROI. This is where
you start = I must have a win percentage of ??? And I must
have a return of ??? What is your sweet spot to satisfy both
requirements? Only then do you know how large your wager
will be.

Thoughts??

in the session you described that there were
only 4 races out of 16 where you used the 88. — Jeff Capper

The 88 is the 1st step always. That determines if the race is chaos or not.
If you can't get the 88% in 4 horses after removing the d and L, you still
used it but only 1 time. If you get your 4 horses, then you go to the Neal.
If you don't get it, then you go to chaos mode.

If you get your 4 horses with the 88% and refire, is there 1 that is obviously
not a contender (mag 9 or whatever your elimination limit is), remove him
and refire. Or you may have 3 strong horses and 1at 3%. He doesn't
make the next 88% and is an elimination. Then the Neal or chaos.

I think that is what we are all working on now is what is the best way to
pare down the contenders and how many times we use the 88% will
be determined by your own personal style.

Maybe???

OK. I just feel a lot more confident if I see the 2 in the bottom remove box
if i am not playing a d and L.

That way, I know they are gone for sure. I guess it's a confidence thing,

Good morning;

I'm babysitting the grandkids right now which is a real pleasure for me. I tend to play horizontal wagers and am hesitant in removing the D's and L's. for this type of wager. For example, I hit the late pick 4 yesterday at Saratoga; three d horses and 1 H5 won the pick 4. The way I tend to play is to use the 88 to get to the contenders, then use the penelope profit button and AB pace screen to finalize my wagers. I also tend to look for a key contender to single in any of my horizontal wagers. I will be trying the elimination method outlined yesterday in truly chaos races and see how it affects my results.