From theory to practice - page 708
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 don't understand if Alexander found what he was looking for... Or gave up.
He flew away. But he promised to come back. (с)
That's not where you're looking, the TV corridor won't let you out...
Differential harassment games. Here theorver may be of auxiliary importance (in data preparation), although you can do without it - everything you need can be provided by filters.
Problem statement :
.
Have you encountered such tasks?Yes, at your suggestion I looked a little bit back last time we were chatting about TI. It seems to me, that they can somehow describe the state of the market, when a big player, like a central bank, plays a big role on it.
I don't know if Alexander found what he was looking for... Or gave up.
Eugene, my friend, once again - as it was, this topic is no longer of interest to me.
It took a year(!!!) for it - the result is +-0% profit. Not that. Deadlock.
I'll repeat - we need a breakthrough topic related to market "memory" research - correlation, non-gentropy, heavy tails... This is the hypostasis of "trend-following" trading. I would love to take part in it - if only there was a person who would start it...
I'm working on Variable Gamma process model, where, fortunately, I don't have to use quantile of the current distribution - the confidence interval limits are calculated automatically. It's also a breakthrough!
But rejoice not yet, there are problems with calculation of expected payoff.
Since this month I am testing a new model. I will surely write upon the results.
Meantime I have no comments. I work and read forum, especially "Random Walking". (A lot!:))))
I don't understand if Alexander found what he was looking for... Or gave up.
Eugene, my friend, once again - as it was, this topic is no longer of interest to me.
It took a year(!!!) for it - the result is +-0% profit. Not that. Deadlock.
I'll repeat - we need a breakthrough topic related to market "memory" research - correlation, non-gentropy, heavy tails... This is the hypostasis of "trend-following" trading. I would love to take part in it - if only there was a person who would start it...
I'm working on Variable Gamma process model, where, fortunately, I don't have to use quantile of the current distribution - the confidence interval limits are calculated automatically. It's also a breakthrough!
But rejoice not yet, there are problems with calculation of expected payoff.
Since this month I am testing a new model. I will surely write upon the results.
Meantime I have no comments. I work and read forum, especially "Random Walking". Bummer! :)))
Not so.
Theory first, then state.
And only then the real thing.
Not like this.
First the theory, then the state.
And only then the real thing.
The theory is all laid out here (see attached file).
Actually, reading this mysterious manuscript, I understood one simple thing - literally ALL of the random process models in relation to the market have been described in English-language literature, and there is no point in repeating them.
1. The reason is that one should grasp the practice of quick TS creation by models. 2.
We should look in the market for TSs already created on the basis of these models and see their characteristics.
The theory is all laid out here (see attached file).
Actually, reading this mysterious manuscript, I understood one simple thing - literally ALL models of random processes in relation to the market, have been already well described in the English-language literature and there is no point in repeating them.
1. You should tinker with the practice of quickly creating TS by models. 2.
2) Search the TS already created on the basis of these models and see their characteristics.
Something that really works would not be described in a book.
So, you can exclude the models described in this mysterious manuscript from consideration.
And monitoring would open the door - the show must go on!
Something that actually works would not be described in a book.
So, you can exclude the models described in this mysterious manuscript from consideration.
And monitoring would open - the show must go on!
Genius.
It's too early to open monitoring - so far the results for Variable Gamma process are poor. Somewhere I have an error due to misunderstanding of expectation calculation. I'm trying WMA now, but I'm afraid it's not the right one.
Now look, Dimitri.
Out of all stochastic process models only two tend to "return to the mean" - Ornstein-Uhlenbeck process and Variance gamma process. Both of these processes are described in this book... So it turns out - ALL stochastic process models on the market - to hell! Right?
If so, moreover, this topic should be scrapped, and a new one should be opened - for non-random processes in the market, processes with "memory".
And one more important comment.
In this thread I tried to understand the "memory" of the market and what parameter it is described by. I was looking for, so to speak, the magic key to the Grail... Couldn't find it...
That is why it makes sense to wait for the unique person who will rise to the forefront of the forum and shout in a falsetto: "I found it! I found the key guys! I know the formula for calculating a really workable market persistence/anti-persistence ratio!!!".
For now, though, this month, I will complete the Variance gamma process. I'll show you the result. What if?!?