Machine learning in trading: theory, models, practice and algo-trading - page 404
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
Golden words Victor Benedictovich..... I still need for Alyosha model in 100? to calculate. Well this is quick, and then you can and file from the first post to calculate. What to do when the TS is trained and works? Right. Follow its signals. But this is terribly boring....
So how about a trading skeleton? Does anyone have one???
Well, in the codebase you can pick up anything for different purposes, it all depends on your needs. Sometimes you don't even need to write anything yourself.
The point is not to have fun, but to make money ;)
Well, in the codebase you can pick up anything for different purposes, it all depends on your needs. Sometimes you don't even need to write anything yourself.
I've already solved the question of data collection and its subsequent processing, so for me this task has already been solved. Now I want to make myself a complete automaton. I want it to check for requotes, communication errors, pick up failed trades, etc. It is important for it to open trades with reliable Kalashnikov's machine. And the signals themselves can be already crammed into it myself.
In fact, the load on the deposit is not small, but the level of profitability is just off the scale. It is true, that it is a heavy load on my deposit, but the yield level is off the scale. This is what they say.....
I solved the issue of my data collection and its subsequent processing a long time ago, so for me this task has already been settled. Now I want to make a full automaton. I want it to check for requotes of communication errors, pick up failed trades, etc. It is important for it to open trades with reliable Kalashnikov's machine. The signals can be written in it by yourself.
It's easy, almost all bots have functions checking whether a position was opened or not, closed or not... everything there is standard and the same for all
In fact, the load on the deposit is not small, but the level of profitability is just off the scale. It is true, that it is a heavy load on my deposit, but the yield level is off the scale. It's a matter of saying what's what to whom.....
Well, try it on another piece of history now, see how long the models live
I'm going to try it on another piece of history now, see how long the models live
Well, the problem is that I don't have any data deeper than the previous contract, I'm already training the model on it for the second day, so I'll check them in battle, as they say in real time...
So the problem is that I have no data deeper than the previous contract, I'm already in the second day of learning the model, so I'll check them in battle, as they say in real time...
Maybe you can find glues somewhere
In fact, the load on the deposit is not small, but the level of profitability is just off the scale. It is true, that it is a heavy load on my deposit, but the yield level is off the scale. It's a matter of saying what's what.....
And do not forget about the task from the first post. Although it is abstract, but it has hidden interactions of predictors. And many systems just do not take this into account. If yours catches these interactions, it will be cool.
Try to teach your system the problem from the first post of this thread. I wonder what will happen...
I'm sorry for interfering, it seems that the question was not for me, but it was just interesting to try it with my generator - the problem is solved in a fraction of a second right in the MQL source code - a forest of one tree and without any R. The source code is a bit big, we're working on it, but it's all in automatic.
Attached file MQH - generated automatically, MQ4 - verification script, to run CSV from the first post of the forum should be in the file folder.
Well the problem from the 1st post I think everyone is interested in checking their MO system.
Interesting generator you have. Is it self written?
Did you divide the plot into 2 or 3. What do you get with unfamiliar data?