Machine learning in trading: theory, models, practice and algo-trading - page 2693
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
Definitely need to write an article about it and post it in the new section.
Judging by the number of articles and the titles, everything has already been decided here.
Our thread is about machine learning, has anyone read it all? The last article is called "... part 25 - a workshop", i.e. a workshop. Some of the articles are called "... part 5." I'm too lazy to read it and I don't have time. Has anyone tried to read it?
There are a lot of articles, very complicated, half of the words I don't understand. I sorted by "best" and took the first one that describes real, practical application.
There are 9 files attached to the article, three of them are .exe files. There are 5 comments under the article - 4 "where to download files?" and 1 negative.
Are there any other working solutions? So that just switch it on and it works. Give me a link.
For comparison in my solution 1 exe file + models and everything works, but it's "duct tape" and "crutches" so I have no chance to get into "machine learning section".
This is proof that third-party solutions are not suitable - people need in-house MQL5 applications.
The author has a series of articles in 2020 , which is listed under each publication:
You need to know the theoretical foundations of machine learning and higher mathematics, otherwise you cannot achieve significant results by superficial manipulation of a few public methods.
To make the "give" mode work, we develop the language of writing trading strategies.
And make them read it before installation, as a guide to safe use
I seriously believe that there is a need for articles on the philosophy of using MO in trading. We need both purely technical articles and articles that look at the issue from a more distant perspective.
I seriously believe that there is a need for articles on the philosophy of using MO in trading. We need both purely technical articles, and those considering the issue in a more distant perspective.
This is proof that third-party solutions are not suitable - people need regular MQL5 applications.
The author has a cycle of articles in 2020 , which is listed under each publication:
The theoretical foundations of machine learning and higher mathematics must be known, otherwise superficial manipulation of a few public methods will not achieve meaningful results.
To make the "give" mode work, we develop the language of writing trading strategies.
You are aware that there are no working solutions in the topic of neural networks and trading at all. They do not exist anywhere, not only in MQL5(koo-koo). There are not even indicators. At least I can't find them. No exchange or terminal offers such an indicator and even less a bot (advisor).
My solution clearly belongs to"superficial manipulation", but it works. An indicator with 65-66% efficiency is just a good indicator among indicators, but in our case it is unique and the only one.
Maybe it makes sense to promote my solution in the MQL5 environment or we will wait for the right people to do something.
You can make a standard ML indicator in MQL5 environment based on my solution. And then develop it if you find better solutions. The topic would revive immediately and a ton of articles would not look so sad.
You are aware that there are no working solutions in the topic of neural networks and trading at all. They do not exist anywhere, not only in MQL5(koo-koo). There are not even indicators. At least I can't find them. Not a single stock exchange or terminal offers such an indicator, much less a bot (advisor).
There are solutions, of course - they invest in this area tremendously. They usually do not show working versions to the public.
Taking into account your words about "complicated language, I don't understand", you don't have serious knowledge, outlook in this topic and understanding of behaviour strategies of companies-developers-calculation-platforms.
Our job is to provide the foundation, democratise and make development cheaper. We have been doing this for more than 20 years: we have revolutionised and implemented many solutions.
I have already said about duct tape - don't ask me to add it, the issue is closed.
There are solutions, of course - they are investing enormously in this area. The working versions are usually not shown to the public.
Taking into account your words about "complicated language, I do not understand", you do not have serious knowledge, outlook in this topic and understanding of behavioural strategies of companies-developers-calculation-platforms.
Our job is to provide the foundation, democratise and make development cheaper. We have been doing this for over 20 years: we have revolutionised and implemented many solutions.
I have already said about duct tape - don't ask me to add it, the issue is closed.
Well, closed, so closed. I'll shut up. Let me know when something working in MQL5 will appear.
By the way, some of your competitors will have something soon. Apparently, the saying "where you are born, there you are useful" does not always work.
I hear about secret developments in secret laboratories all the time.
You are aware that there are no working solutions in the topic of neural networks and trading at all. They do not exist anywhere, not only in MQL5(koo-koo). There are not even indicators. At least I can't find them. Not a single stock exchange or terminal offers such an indicator, much less a bot (advisor).
My solution clearly belongs to"superficial manipulation", but it works. An indicator with 65-66% performance is just a good indicator among indicators, but in our case it is unique and the only one.
Maybe it makes sense to promote my solution in the MQL5 environment or we will wait for the right people to do something.