Machine learning in trading: theory, models, practice and algo-trading - page 2508
![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
An outsider's view of the branch, no offense
There are two gentlemen sitting in the back of a cab talking.
- Can you imagine - yesterday in the restaurant, when the waiter was pouring wine, there was no napkin on his hand.
- You don't say... Yes... I was in a restaurant with a lady the other day, and the waiter gave me the menu first...
- No way...
The driver was sitting and sitting and then he asked:
- Gentlemen, is it all right if I sit with my back to you?
I once encountered a painfully logical question on the web
If I wrote the same code as a 100-line code in 10 lines, performing the same functionality - does this mean that I am worse at programming and my work should cost less
The answer, I think, is obvious to all!
so the point of this thread is not to gather a flock looking for a scapegoat to fulfill their "requests" (which they achieve by their rudeness, thinking that the bigger yell, the newbies will join, because they, yelling, which some try to turn into a development with the slogans "join the team" ("because I learned more words, though I don't understand all of them completely, I'll leave that out")...
and the goal of adequate development is to find convenient libraries that give an opportunity to concisely express in code your strategy of approximation and optimization of info entering the market and trading based on it...
But you can't code and automate anecdotes with an adequate development approach ... (someone is at least interested in the topic, and someone is in order to trawl anecdotes) -- not the place... -- also, by the way, a question of adequacy...
all modeling often comes down to looking for correlations or the lack thereof (in addition to approximation) and drawing conclusions... Trying to break into MQL tester and optimizer and make it your own algorithm and from your own signals is a non-trivial task...
... There will always be some random people in the thread, who won't be able to overcome the next step after the anecdotal view of the market... ...so they go around off-topic, butting into conversations they're not old enough to have... -
You guys, you've got an upset girl here... What are you doing here? She's smart, she's probably beautiful, and you're just trying to show off your skills, you braggarts.
... there's always the occasional person on the subject,
Why, I read you very carefully, and I like what you have to say. Don't be so serious.![](https://c.mql5.com/3/373/give_rose.gif)
You guys, you've got an upset girl here... What are you doing here? Intelligent, probably beautiful, and you're here to measure the skills of each other, braggarts.
We impose on you this honorary duty (and sacred duty) to adjust the upset girl)
I once came across a painfully logical question online
the answer, I believe, is obvious to all!
so the essence of the branch is not to gather a flock looking for a scapegoat to fulfill their "requests" (which they achieve by their rudeness, thinking that whoever yelled the most, the newcomers will join, because they, yelling, which some try to turn into a development with the slogans "join the team" ("because I learned more words, though I don't understand all of them completely, I'll leave that out")...
and the goal of adequate development is to find convenient libraries that give an opportunity to concisely express in code your strategy of approximation and optimization of info entering the market and trading based on it...
But you can't code and automate anecdotes with an adequate development approach ... (someone is at least interested in the topic, and someone is in order to trawl anecdotes) -- not the place... -- also, by the way, a question of adequacy...
all modeling often comes down to looking for correlations or their absence (in addition to approximation) and drawing conclusions... Trying to break into MQL tester and optimizer and make it your own algorithm and from your own signals is a non-trivial task...
... There will always be some random people in the thread, who won't be able to overcome the next step after the anecdotal view of the market... ...so they go around off-topic, butting into conversations they're not old enough to have... -
Aren't you tired of being rude? She hasn't said anything sensible, she just said a bunch of meaningless words.
Exactly. I think everyone who responds to her has never heard the proverb about the egg that you don't have to eat to understand it's rotten
We impose on you this
Thank you, friend.![](https://c.mql5.com/3/373/drinks.gif)
I feel that I will incur the wrath of the local IO intellectuals/alumni, but I will risk asking a question. Who thinks what indicators (other than built-in or the most popular ones) are the most interesting for the forecast? For my part I'm currently experimenting with combination of exponential moving average (DEMA) with Kalman filter and fast Fourier transform (separately). But first I make predictions using a neural network. Once again I clarify, I'm not asking for application results (or now the nice girl is going to spew a bucket of garbage again).
Who thinks what indicators (other than built-in or the most popular ones) are the most interesting for prediction?
Of course the neuronists here are authoritative, and they know how to squeeze the most out of data in the fight against overtraining, but in my opinion, it is the input data that is the main problem. Any oscillator (standard or self-written), or any continuous curve, does not contain the regularity of price, so we can't teach the guinea pig properly.
I see the following way: trends and their waves. The wave length, the interval of time of the wave, the speed of the wave, a comparison of these parameters with the previous ones, the size of the excess of the previous extremums (trend movement), the distance to the nearest non-crossed extremum in the past, ... ...there are a lot of things that can be compared. I think there are regularities here, that is what you can indulge in with your grid,
or you can think for yourself.![](https://c.mql5.com/3/373/Pensive.gif)
I feel that I will incur the wrath of the local IO intellectuals/alumni, but I will risk asking a question. Who thinks what indicators (other than built-in or the most popular ones) are the most interesting for the forecast? For my part I'm currently experimenting with combination of exponential moving average (DEMA) with Kalman filter and fast Fourier transform (separately). But first I make predictions using a neural network. Once again I clarify, I'm not asking for application results (otherwise sweet girl is going to spew a bucket of slop again).