Machine learning in trading: theory, models, practice and algo-trading - page 1960
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
A grid with 1 neuron and 1 input produced. 1.7 million ticks. It has 0.618 profitable trades, 0.38 expectation. If you want to check it, I will send you the original series.
I tried to filter filter by saber. I do not know yet how it works, but it seems to be able to analyze spread.
I have not understood how it works, but it should count spreads. 0 filter. There are 0.598 profitable trades. Expected payoff is 0.019.
Filter 5. Profitable trades 0.79. Expectation 0.0487.
I filtered by saber, I do not fully understand how the filter works, but it seems to take into account the spread.
Filter 0. I have 0.598 profitable deals. Expected payoff is 0.019.
Filter 5. Profitable trades 0.79. Expectation 0.0487.
What is it, can you provide more details?
what is it, can you be a little more specific?
Saber in the article uses a tick filter to reduce calculations. As I understand it, 0 removes fluctuations smaller than the spread, 5 sort of widens the spread by 5 pips.
The grid on such data still sees a pattern, although the mat expectation is less than the spread, but the network is only 1 neuron, 1 input.
In general the grid has found something, it makes sense to keep digging. I have nothing more to add at the moment.
Saber in the article uses a tick filter to reduce calculations. As I understand it, 0 removes fluctuations smaller than the spread, 5 sort of widens the spread by 5 pips.
The grid on such data still sees a pattern, although the mat expectation is less than the spread, but the network is only 1 neuron, 1 input.
In general the grid has found something, it makes sense to keep digging. I have nothing more to add.
Ok, thanks.
There was a guy here who offered $100k for a cool bot on NS. Let him make a contest on cagle...
but too bad he's just a f---ing liar)
But it's a shame he's just a f...l.)
That's for sure... And a dumb f...l.
By the way the patterns with time didn't pass the reality test((.
That's for sure. Plus the stupid p...l.
By the way, the time patterns didn't pass the reality test((
I don't have an ace either.