Machine learning in trading: theory, models, practice and algo-trading - page 442

[Yuriy Asaulenko]

elibrarius:

Anybody can show you the tester data. You put it on a real or demo.

Or not in the real time, watch the behavior of the strategy, and valking forward testing do for six months to a year ... So train on data till March and check it in March, then train on data till April and check it in April and so on. In real time, it's too long to wait to evaluate an EA's performance.

From my own experience, the real is not much different from the test. However I am using my own tester. How MT tests it, hell knows.

[Mihail Marchukajtes]

Today is not a good day.... If TC is really wrong, she's doing it in a big way. It's a kind of payment for extra profitability. But I would not want to start from this very place :-(.

Either that is the answer, that the TS has stopped working, do another one. BUT for a week I'll still see..... Either it's a temporary hiccup that will more than pay off in the future. It is important what happens next, right? :-)

[govich]

Mihail Marchukajtes:

Today is not a good day.... If TC is really wrong, she's doing it in a big way. It's a kind of payment for extra profitability. But I would not want to start from this very place :-(.

Either that is the answer, that the TS has stopped working, do another one. BUT for a week I'll still see..... Either it's a temporary hiccup that will more than pay off in the future. It is important what happens next, right? :-)

You've written that you trade with limits, that is probably a channeler, while channelers are like options selling, like a stable growth of small change by weeks and then bam! And in a couple of hours everything goes down the toilet.

[Mihail Marchukajtes]

govich:

You wrote that you trade with limiters, that is probably a channeler, and channelers are like selling options, like a stable growth by small amounts of weeks, and then bam! and in a couple of hours everything goes down the toilet, it is also so in the tester, with zero profit expectation.

All right, all right, one mistake leads to a loss, I set the stop loss level at 40 pips. Especially two decisive signals came to the class "I do not know" and mistaken..... All right, we'll think of something.

And I have a question for experts. How do I take the data from the low timeframe? How in MT4 is it adequate????

[Alexander Ivanov]

I don't understand you

Why did you make some pending orders on the artificial intelligence?

If pending orders, then it's not a highly intelligent bot)))

[Vizard_]

Mihail Marchukajtes: It's important what happens next, isn't it? :-)

http://radikal.ru/video/Rv6hGGmBVSZ

[Albinochka6]

I tried to read a book on machine learning, not even to master it, but just to start reading it - I could not, it was very difficult and I understand that the topic is really good to study, probably not enough life.

[kaliteran]

Vizard_:

http://radikal.ru/video/Rv6hGGmBVSZ

waw! 90% accuracy is awesome!

[Alexander Ivanov]

The whole thing is a load of bullshit with the pauses. And you consider this to be AI?

[Ivan Negreshniy]

Albinochka6:

I tried to read a book on machine learning, not even to master it, but just to start reading - I could not, it was very complicated and I understand that the topic is really good to study, probably not enough life.

That's probably what they said in Kulibin's time, when he was making his pocket watch with music and dancing, and now everyone has plenty of that, plus video communication, navigation, internet and machine learning are already everywhere, but the Kulibin spirit is alive...