Machine learning in trading: theory, models, practice and algo-trading - page 2862
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
Why hasn't the issue of how to reduce overtraining been addressed?
So decided - the number of parameters to be optimised should be minimal - for this purpose it is necessary to exclude NS from the algorithm.
About understanding. If I don't see why some data should influence the price + there is no information about it in the network, then most likely Caroline other participants are not aware of it either. Accordingly, they are not needed - nobody takes them into account in trading.
Well, let's ask GPT
any abstruse mess can be represented by a few lines of code, no more than 10.
However, I didn't peek and came up with it myself.
So decided - the number of optimised parameters should be minimal - for this purpose we should exclude NS from the algorithm.
Let's say you have a basic idea that gives 55% of profitable deals, but in financial terms it turns out to be about zero. And here you want to increase the number of profitable trades - what are your actions?
About understanding. If I do not see why some data should affect the price + there is no information about it in the network, then most likely Caroline other participants are not aware of it either. Accordingly, they are not needed - nobody takes them into account in trade.
And if you have found derivatives of what others take into account in trade?
And in general, it's such a variety of who takes into account what.... it's harder for me to find what they don't. You took oscillators as predictors and found a pattern there - many people use them - is it a reliable pattern right away?
Let's say you have a basic idea that gives you 55% of profitable deals, but in financial terms it turns out to be about zero. And here you want to increase the number of profitable deals - what are your actions?
Here are the real steps that I have taken - thrown out. And sat down to write an Expert Advisor that trades futures against spot, what prostotrader wrote about in the neighbouring section. I finished it up to the point last week - I can't improve anything else within MT5. In the process of writing and trading a lot of ideas were born. Now I'm closely engaged with them. But everything is market-neutral. I don't plan to return to directional trading.
As soon as I get something worthy of attention, I will definitely report on the results. But at my pace it will not happen soon....
Here are the real steps I took - I threw it out. And sat down to write an Expert Advisor that trades futures against spot, what prostotrader wrote about in the neighbouring section. I finished it up to the point last week - I can't improve anything else within MT5. In the process of writing and trading a lot of ideas were born. Now I'm closely engaged with them. But everything is market-neutral. I don't plan to return to directed trading.
As soon as I get something worthy of attention, I will definitely report on the results. But at my pace it will not happen soon....
Well, you should have said that you gave up directional trading.
Does your broker give EBS on MT5? And, what about the CS? Isn't it forbidden to keep depo in dollars? There is a point in artificial leverage, isn't there?
Does your broker give EBS on MT5? And what about the CS, I thought they banned holding a depo in dollars? The point is artificial leverage, isn't it?
Fi-am, EBS gives.
I have ruble CS mostly. With leverage after forex there everything is not humane - it is better not to use it.
I won't answer all the nuances - there are really a lot of them there. There is a branch, everything is described there in detail.
The entry threshold for the sum is much higher than forex. And this strategy is not much of a bargain - it is rather an alternative to a bank deposit + a good opportunity to gain invaluable experience in trading on the stock exchange. But there are no drawdowns if you don't make mistakes :)
I have an idea for simulating the actions of market participants...
This logic doesn't fit:
1) Influence of large non-speculative players. This is primarily states and intergovernmental organisations.
2) The influence of unexpected news.
3) Combination of the first points, when states react in an unexpected way to unexpected news.