Bayesian regression - Has anyone made an EA using this algorithm? - page 49
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
I admit that you have a robust TS. Only you don't take into account the floating spread, nor do you take into account that on another broker on the same symbol it may not work even in the tester.
Each symbol has its own pattern. The history of each symbol depends on the broker. When, like you, you get a paltry mathematical expectation, you have to realise that these features are affecting and very seriously. And complex mathematics can run into the Butterfly effect. When the underlying data is slightly different (a different broker or spread) kills or exalts the next mathematical model.
And you may have had the grail in your hands. But only you didn't know it was a grail not on the majors but on some GBPCHF. And not on Alpari, which you used to test, but on some FXCM. So you may have thrown this grail away, not knowing that you held such a great mathematical model, but rejected it just because you did not know about GBPCHF and FXCM.
I tested it on majors, all that deserved attention on that page. The maturity expectation on EUR is even very big (0.00063), taking into account the spread 0.0003.
On other pairs the EA logic did not work as well.
But I did not reject it. I wrote somewhere that I was using it for more than half a year on a standard account and my greed overcame me after 8 months. Advisor was showing purely 20-30% over that period, with planned 50-60% per annum. Well it's just that the unevenness of the time of winning pips was annoying.
I'll repeat that there is one simple idea in there + a couple of tricks that are also attached to other EAs.
On the fingers of two hands I've only seen TC trades that were really robust during their time on the real. They made thousands of percentages and many hundreds of thousands of USD. Only one of them was on the major - GBPUSD. All the others worked on crosses with much better results.
The choice of crosses shows that it is easier to find the correlations between currencies (except USD) than between currencies and USD itself. The question is why do mathematicians always pray for major currencies in their articles? Why the hell should I apply complicated mathematics where it is the hardest? For the love of the "hammock"?
And yes, the robust systems that earned a lot more than the "quonts" stopped working after a while. But the final bank account the authors increased very seriously. That is, they identified a pattern and were able to trade it very effectively. And then the pattern went away. So was the art in identifying a pattern that would break? Or was it in the mathematical methods that supposedly by the next mathematical criterion show something there with a certain probability.
The authors I knew applied the most primitive logic. And they themselves were shocked that it works. But the complicated one does not. You should talk to more practitioners of big earnings in this business. All of them are good at maths, at best at the level of the 10th form of a Soviet school.
On the fingers of two hands I've only seen TC trades that were really robust during their time on the real. They made thousands of percentages and many hundreds of thousands of USD. Only one of them was on the major - GBPUSD. All the others worked on crosses with much better results.
The choice of crosses shows that it is easier to find the correlations between currencies (except USD) than between currencies and USD itself. The question is why do mathematicians always pray for major currencies in their articles? Why the hell should I apply complicated mathematics in the place where it is the hardest? For the love of the "hammock"?
And yes, the robust systems that earned a lot more than the "quonts" stopped working after a while. But the final bank account the authors increased very seriously. That is, they identified a pattern and were able to trade it very effectively. And then the pattern went away. So was the art in identifying a pattern that would break? Or was it in the mathematical methods that supposedly by the next mathematical criterion show something there with a certain probability.
The authors, that I knew, applied the most primitive logic. And they themselves were shocked that it worked. But the complicated one does not. You should talk to more practitioners of big earnings in this business. Everyone is good at maths, at best at the level of the 10th form of a Soviet school.
I might jam the next cross analysis experiment. Thought about it. And as for the dudes who have made a lot of money, they may not really come up with anything after that due to the fact that they were just lucky enough to find a short-lived pattern once by trial and error, and lack the skills to plough through the entire field of possible patterns.
Yes, they have skills. They don't suffer from cap-assassination and other starry-eyed bullshit. Really experienced guys. And the results are sometimes repeated.
Can you give me a link to monitoring at least one of them? You may write it in your personal message.
And there is no monitoring. They only monitored their first trade and there is no need to monitor the next ones. Nobody shines a light on it. The issues of brokers and withdrawals are ironclad with them.
But no one comes up with anything fundamentally new, it seems. When you ask. Basically, it's the art of not losing and getting it right.
Everyone has the same list of trading symbols. They use pricechannel, averages and zigzags with daily trading intervals. They usually trade every weekend and for a month/evening. No one cares about the results of a tester that shows half a year ago. No one is looking for grails. Just polishing up what they have. And they experiment a bit with MM, grids, portfolios and so on. Trying to reduce drawdowns rather than increase profits.
Not a single profitable martin and grider. I know of one over-exposure who made several million USD in profits on GBPCAD. But that's not my approach, so haven't even tried it. I need at least five trades a day for one symbol. Then at least some drop in the direction of stat validity.
You should talk to more practitioners of making a lot of money in this business.
Where else would you find practitioners who are willing to share how they make money?
I have not been able to do so, so I have been working on my own and am still working on my own.
Where else are these practitioners willing to share how they make money?
Those who have been managing PAMMs with large sums of money for more than a year usually have this knowledge. Get in touch with them through the same Skype and ask them. You will be in a good mood and you will probably have a good conversation. They don't really talk to each other, there's no need for that. Everybody understands everything. And only the one who has had it bad for a long time asks more questions. The rest just work.
The maximum you can find out is the trading style, what indicators they use and the symbol. The rest is up to you. This is the right thing to do. And not once have I heard even a hint of linear algebra with statistics from anyone. Let alone anything more complicated.
I think now with the new tester they are going to try something new.
Those who have been managing PAMMs with large sums of money for more than a year usually have this knowledge. Get in touch with them through the same Skype channel and ask them questions. You will be in a good mood and you will probably have a good conversation. They don't really talk to each other, there's no need for that. Everybody understands everything. And only the one who has had it bad for a long time asks more questions. The rest just work.
The maximum you can find out is the trading style, what indicators they use and the symbol. The rest is up to you. This is the right thing to do. And not once have I heard even a hint of linear algebra with statistics from anyone. Let alone anything more complicated.
I think now with the new tester they are going to try something new.
It smells like Ilano-Martin. 95% of Pamm managers are like that. You snatch, you withdraw, you're happy. They dumped it, it's not theirs, and that's fine. A small number of PAMMs are stable systems that have been around for many years, often semi-rugged.