Surprisingly, it was only the ones that actually had big payoffs, as I recall. LOL

Did you check out the Chaos5 races with A+ horses on Friday?

(I only looked at Friday.)

Just to be clear... Last November's races were not included in the training set. The AI was trained during the summer and for Graded races I went all the way back to 2013.

Must be some good things! — Mark

Truly.
They're working on how to win and I'm working on documentation.

Where's everyone at? — Mark

Lots going on under the hood.

Dave Schwartz, some questions for you:
What do you consider deTerminator's best feature (AI Line, AI Best Horse Pct, $Net, ...) to be, and why?
What is the easiest way to apply it to generate profits? — Tom Atwater

Considering what I've been working on for the last week, I'd have to say:

"THE BEST FEATURE" is NONE OF THE ABOVE!

Brian and Tony have the prerelease. Maybe they can give you a first impression.
Ping @ponyplayer & @Tony Kofalt

I hope to have it finished by tomorrow night.

35 fixes it and is in your DropBox.

It's working but I left in a stop.
I'll explain all of this tonight.

But Upgrade coming to get rid of the UNNECCESSARY stop.

Dang.
Upgrade in 15 minutes

Georgeontherun-- good name for a race horse. — Jim Pommier

LOL
I like it!

As I always say when new people come over...
"$500 for the bird and the cage."
They say that they're not looking for a bird.
Then I say, "How about I give you $800?"

It is not.

There is no replay.
A big bug was discovered and, while the lesson was clear, it was dwarfed by the bug.

Took me 19 hours to find and solve that bug.
But in the end I was the victor.

We had a meeting tonight where a similar but better version of the lesson was presented.

“A priori” would be precisely correct, As it is , As it is somewhat Bayesian In nature.

(Sometime dictation drives me insane.)

You guys probably want the v1.0027 upgrade.
Link to discussion

Agree with everything that ponyplayer said above. Another tactic is concentrating (at lease initially) on horses that are bet way down from their AI line. For these horses then try including additional factors such as rank and margin and grade (I've found that horses in the "A" range tend to do well). As you get better with experience you will come up with other ideas, broadening and improving your approach. — Neal Freedman

I see it the same way as both you & @ponyplayer.

What the AI Line gives us is a standard to measure the gate odds (or whenever) against.

Is the AI Line an estimate of what the whales are using to estimate the true probability of a horse winning the race?
That is, is it an estimate of the line the whales compare to the post time tote odds, then essentially bet the overlays in some fashion? — Tom Atwater

The AI Line is literally how the entire public should bet the horses based upon past history.

Imagine you have a horse who IS 1/5 on the tote board.
How did he get that way?

Most of the time, if you were to look at the key betting factors you would find that this horse was ranked 1st for just about everything.

In other words, he is likely the best horse in the race.
_____________
The roots of the AI Line trace back to a column in HSH IV Tables - The "BV" column - which stands for "Betting Value." Simply put, that is an IV-type representation of the expected percent of pool that should be wagered on each horse.

Dave, what plans do you have for deTerminator documentation in general? — Tom Atwater

That could be a long answer but, in my newly made commitment to brevity, I will say that it begins with a new approach. Still videos, but very short and mostly based upon screenshots.

The onboarding process is really the key - and the team will help with that greatly.

Thank you.
We seem to be doing pretty well.

That's because you did not tell me who you are beyond "Bob, a customer."

I need the workout reports — bob

Please send me a private message detailing who you are so I can send them via email.

Welcome back!