Discussion of article "Grokking market "memory" through differentiation and entropy analysis" - page 2
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
The Tester is missing one thing that was planned to be added, but due to complexity has not been added yet. Due to the fact that a linear trend is taken into account, it does not work correctly on new data when the trend changes. It can be cured by estimating the variance around the trend line on the training sample and compare it with the new data, if the variance has increased then do not trade. These are subtle tricks that are not obvious to those who are not familiar with the MO.
You don't understand me at all. I was not talking about the TS, but about evaluating its results in the standard Tester.
Stat results on the table!
Are they mine?
Here:
What do you need them for?
I'm talking to Max, not you - although, you're absolutely right about CLOSE prices.
I use an entropy-like breakdown indicator in my TS and it would be a disaster without it.
Once again - Max's research is doing the right thing, the transition to ticks should be gradual as you understand the relationship between ticks and market timing and a TS based on MO should work at the lowest process entropy values. You get it? That's right. Learn while I'm alive.
You didn't understand me at all. I was not talking about the TC, but about evaluating its results in the standard Tester.
What do you need them for?
At least some argument in evaluating claims of correctness.
I'm talking to Max, not you - although, you're absolutely right about CLOSE prices.
No, it's just a hypothesis with some pretty good reasoning behind it.
In my TS I use an entropy-like discord indicator and without it it would be a disaster.
Well, in other TS it is not used, but they managed to bring profit on many thousands of trades during months on real.
Once again - Max's research is correct, the transition to ticks should be gradual as we understand the relationship between ticks and time on the market and the TS based on MO should work with minimum values of process entropy. You get it? That's right. Learn while I'm alive.
Schoolboy, apparently.
Well, other TSs do not use it, but they managed to bring profit on many thousands of trades for months.
Schoolboy, apparently.
What trades, Uncle? Are you in a delirium of arbitrage or what?
You're talking about the physics of the process! Anyway, it's all right - we've never talked and this conversation is unnecessary.
Good luck to you, Garibaldian!
What kind of deals, Uncle? Are you in a delirium of arbitration or what?
Honest trades. No technical insider trading or cheating.
Positions that don't overlap in their lifetime. Entry and exit levels are written many seconds before they're triggered.
Honest trades. Without technical insider and other cheating.
Deals that do not overlap in their lifetime. Entry and exit levels are prescribed many seconds before they are triggered.
No, well - well done.
I can see that you have authority on the forum, but our positions will never become closer.
By virtue of education, obviously:))))))
I can already see that you have authority on the forum, but our positions will never become closer.
There is no desire to get closer. I spoke out because sometimes there is another desire - not to silence irritation at people who do nothing, but think they have the right to assert without any arguments what is right and what is wrong. Saying that something should be done and what should not be done.
I will assume that my position on this issue will be understood by many. I may be wrong, of course.
There is no desire to get closer. I spoke out because sometimes there is another desire - not to silence irritation at people who do nothing, but think they have the right to assert without any arguments what is right and what is wrong. Saying that something should be done and what should not be done.
I will assume that my position on this issue will be understood by many. I may be wrong, of course.
OK.
The only thing is that I would like Max not to miss the main point because of our squabble - there is nothing to do on OPEN/CLOSE M1 and above from the word "absolutely".
And whether to switch to ticks, whether to thin them, whether to use entropy - I think he will decide for himself.
That's all.