Machine learning in trading: theory, models, practice and algo-trading - page 224
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
Three wise men were walking along a road, on the way they met a fool, and the fool asked the wise men - what is the meaning of life?
....... The two wise men walked along the road, and the two fools were left to speculate about the meaning of life.
When you talk, it looks like you're delusional.
Show me the answers to your points in any language! Do you have such answers? What does R have to do with it?
Or do you have a grOal on the mcl?If R language has no built-in algorithms of pattern recognition (just like MQL), then what are its special advantages? The fact that it's supposedly easier to create such algorithms? Then why haven't they been created yet? If so, where are they?
Maybe the point is that R just became trendy in trading, but not because of his special merits, but because there was a change in trading ideas? That is, the classical technical analysis has become a thing of the past, and "sophisticated" and "exotic" methods of data analysis have become very popular.
Higher mathematics and statistics have become tools for analyzing market data and making trading decisions. And here R, as a language specialized in this category of calculations, appeared on the scene. How effective is the use of such analysis methods in trading - an open question. No one has proved it.
No iron evidence of the found market laws with the help of statistics and higher mathematics has been presented. Just these methods have become fashionable, and therefore R has become fashionable.
However, the actual statistical study of the effectiveness of mathematical and statistical methods for analyzing market data and finding their patterns, it may turn out that the classical technical analysis is much better, and therefore the benefits of R in algotrading in comparison with MQL is not proven.
If you want, let's research the effectiveness of "trendy" new analysis methods using machine learning and other "tricks" in R, and compare with the trading results of the usual technical analysis (support lines, correlations, breakdowns and rebounds, trends, etc.) in MQL.
Let us draw the final conclusion about the benefits of the R language in algotrading.
And to finally separate "cutlets from flies", I will say that R can really have advantages, but how valuable they are in trading is an open question.
If these advantages do not make strategies more profitable, they are of no value for algotrading.
As for the ease of writing code and using ready-made templates, - this is an "advantage" only for users.
For developers, it is preferable to understand their code in detail.
As for the ease of writing code and using ready-made templates, - this "advantage" is only for users.
It's preferable for developers to understand their code in detail.
So write your own trading platform, what for do you need mt5 and mql, you are a developer, but not a user, right? )))
Why should you take someone else's code, it's just stupid, you contradict yourself))))
So write your own trading platform, why do you need mt5 and mql? )))
Why take someone else's code, it's stupid, you contradict yourself ))))
I have no disrespect for users. You make it sound like that for nothing.
Users just don't understand that ready-made solutions, templates and standards are only good for them. What developers need is the ability to break them and build their own templates and standards. This allows you to change the direction of development and open up new horizons.
Otherwise, - only following within the established framework.
I have no disrespect to users. You shouldn't make it sound like that.
Users just don't understand that ready-made solutions, templates and standards, are good only for them. What developers need is the ability to break them and build their own templates and standards. This allows them to change the direction of development and open up new horizons.
Otherwise, - only following within the established framework.
1) Well, who forbids breaking? All codes are open in p-ka, break them as you please.
2) If you already have a solution that suits you but you need to use it, no matter whether you're a user or a pro, it's hard to argue with this.
So write your own trading platform, why do you need mt5 and mql? )))
Why take someone else's code, it's stupid, you contradict yourself))))
1. Have I ever said otherwise? Where did I talk about trade orders? What do you mean?
2. Well, isn't it ignorant to look for evidence that the future will be the same as the historical data?)) Statistics collect data as a basis for identifying patterns, but cannot serve as "proof" of them. A pattern identified by statistics is speculative. You can see the pattern, I can't. And vice versa. Therefore, your "proof" based on statistics is an erroneous conclusion and acceptance of a subjective vision as an objective reality.
In trading, statistics is an analysis tool along with indicators, patterns and other types of pattern detection. Everyone decides for himself how to use it. For many people statistics is necessary only for evaluation of trading results, for others - for searching of market dynamics repetitions, for others - for checking quality of indicator signals and so on... However, any unambiguous conclusions about the future based on collected statistics are a delusion. Therefore, don't "idolize" statistics - their value in predicting recurrences should also be statistically verified. So, - gather statistics on the accuracy of your statistical predictions, and then statistics on those statistics, and so on...)
Now about machine learning: where are the fruits of its effectiveness? Can you write a universal R code to detect classic price formations? I need the algorithm to find trends, flotsam, levels, breakdowns, rebounds, corrections, parabolic curves, channels and many other things without errors. All this is technical analysis. If R was originally designed for trading, such algorithms should be implemented by default. Where are they? If they are there, what are we arguing about? - R is the best language for trading!
And so, the proverbial machine learning: neuronets must be able to recognize price figures easily, and not inferior to humans in this skill. Can they do it? Where is the proof? Show me a robot on R which recognizes all the patterns and then I will say that you are right about everything.
3. R I don't know, and my ignorance is definitely there. However, if you prove its efficiency to me in practice (by presenting trading results, or a robot that can solve the above mentioned problems), then I'll be glad to study R.
But while supporters of R saying "why reinvent the velocipedes?" suggest using crutches, the adherents of MQL will make their own bicycle on which they will surely outrun waddling opponents.)
The TA does not need to be opposed to statistics and MO, many "indicators" are classical statistics, their windowed version, while the optimization of TS on indices is a particular case of MO, for example easily reduce the wires to a neural network, the difference between TA and MO, in the first place, that the latter, so to speak "more scientific",It means, its methods are not proved strictly mathematically, at least numerically, empirically; and in TA there are a lot of groundless hypotheses and different methods that appeal only to "common sense", which often only harms than helps in trading.
1) well, who forbids breaking? in the r-ka all the codes are open, break as you please
There are no contradictions in his words. You may connect to broker on FIX with your own trading program, written in C, for example, and trade even without using MT and still carry out the whole spectrum of technical analysis in your C-creation. But the thing is that it is easier to do it in MT, not in R or in C, but with the program written in MQL in MT. For MT there are mountains of special trading "bricks" freely available in the code base, from these bricks the green trader can create his fantasies. There is a generator of advisors, if you want you can get inside the code and understand in details how everything works (without the need to read tons of scientific literature of academicians who created this module, like SanSanych does).
Well yes, I agree, and I won't argue...
But if you want to check some machine learning algorithm for the market, one of 10 popular algorithms and pre-process the data before that in any of 50 known ways, then R-ka will do, and this thread is just about it....
Every language has its own task, what's there to argue about ...