Machine learning in trading: theory, models, practice and algo-trading - page 2151
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
One of the standard approaches is the same CUSUM. Only it is applied not to the price increments, but to the errors of the model used.
Yes, the essence is the same. Everything is open before us.) But in code it is difficult, endings without errors with unambiguous solutions in the same conditions is difficult in BP with SB.
That goes for you, too. The grail is needed, you see? It's not a quibble.
Eh remember the time when the forum appeared AK with his shadow AK2 and Schrödinger's cat, as he said - 'now I'm this market like two fingers .... and show everyone the Grail', how many arguments were there with the potato boss and Asulenko .... Eh...and where are those interesting times, inspiring the suffering?
Time has passed since then, the cat ran away, Toddler appeared ..... and where is the Grail?
If in an already marked dataset with labels, you subtract or add a spread from the features, depending on the label, what effect would this have?
Will the feature space look better separable?
It is clear that this is done only for training.
Eh remember the time when the forum appeared AK with his shadow AK2 and Schrödinger's cat, as he said - 'now I have this market like two fingers .... How many disputes did he have with kartofilny bos and Asulenko .... Eh...and where are those interesting times, inspiring the suffering?
Since then, the time has passed, the cat ran away, Toddler appeared ..... and where is the Grail?
And how else to cheer up the residents of this branch? Flattery and rudeness will not do... After all, we need results, no matter how you look at it. And not test results, but at least on demos.
Toddler stopped broadcasting because he doesn't see the point in 10-15% per month. This is very little, and he is not capable of more, alas....
But hope dies last and the eyes of those who suffer are turned toward the MO. We wait, we hope, we believe...
And how else to cheer up the residents of this branch? Flattery and rudeness is not the answer... After all, we need results, no matter how you look at it. And not test results, but at least on demos.
Toddler stopped broadcasting because he doesn't see the point in 10-15% per month. This is very little, and he is not capable of more, alas....
But hope dies last and the eyes of those who suffer are turned toward the MO. We wait, we hope, we believe...
If you have 10 lem on your account, then 10% is already 1/20 of a lamb
No, well, not everyone is able to have such a deposit. That's why single traders have to look for the Grail. Without it - only to the factory.
No, well, not everyone can have such a deposit. That's why single traders are forced to look for the Grail. Without it - only to the factory.
I need an effective function that will put a spread in the feature space
I need an efficient function that will put the spread in the feature space
Maxim, the spread is the difference between buying and selling - ask and bid, head-on.
And if you think about it, it's the difference between the average buy price and the average sell price.
Swap those two prices.
Then you'll have the market and the spread.
Maxim, the spread is the difference between buying and selling - ask and bid, if you think about it head-on.
And if you think about it, it's the difference between the average buy price and the average sell price.
Swap those two prices.
Then you'll get the market and the spread as well.
That's right, Rinat. To know the price of an instrument, you must swapthese two prices.
====
At least one person showed the sense of the price.
.