Machine learning in trading: theory, models, practice and algo-trading - page 1576
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
Something tells me that this is how you find the fundamental trends. And as you yourself have come to the conclusion that yes, it could end in a year or two, or tomorrow. It's business as usual. If your system gives such rare entries, then there is nothing to do but to rely on it, having previously (as Maxim has already noted) analyzed and determined the patterns, whether they are contradictory and random.
The problem is that we open an order today and close it almost a year later (10-12 months)
and then we risk to take some time to find out if a "fundamental trend" has come to an end (((
But it does not matter
On other TFs there may be other settings, and we still do not know how to relate to them, if the settings are not some random, but work within a fairly large range of parameters
well, why do we need to advertise courses?
the grain of the video about the application of DSP to the market...
This video answers to 99% of questions which are discussed here.
a video about the application of DSP to the market...
DSP answers 99% of the questions discussed here in a formalized, scientific way...
Yeah, momentum + std. Very informative.
the forward is not deals, but the quality of the synthetic or its probabilistic characteristics
Then what is the criterion of quality?
And at what period can we talk about confirming this quality?
If it is the same deal (and its profitability), then yes, 10 months of forward is not enough.
Then what is the criterion for quality?
And at what period can we talk about confirming this quality?
If it is still the same deal (and its profitability), then yes, 10 months of forward is not enough.
There can be many quality criteria. For a synthetic it can be a constant MO or variance.
If the average deal lasts 4-6 months, then the forward is 6 months. After that, the system can be over-optimized.
Fools who think that the model can "work" for a year or more without loss of quality will be punished by the market itself. It's only the morons who test advisors on a sample of 10 years... Well, also maxima....
There can be many quality criteria. For synthetic it can be constant MO or variance.
If the average trade lasts 4-6 months, EXAMPLE, then the forward is 6 months. After that, the system can be over-optimized.
Fools who think that the model can "work" for a year or more without loss of quality will be punished by the market itself. It's only the morons who test advisors on a sample of 10 years... Well, also maximka....
he does it right
Until you get a model that gives not even 10 years, but the whole history, which dumped 200-300% per month, you can safely in the group that you mentioned
There can be many quality criteria. For synthetic it can be constant MO or variance.
If the average trade lasts 4-6 months, EXAMPLE, then the forward is 6 months. After that, the system can be over-optimized.
Fools who think that the model can "work" for a year or more without loss of quality will be punished by the market itself. It's only the geeks who test their Expert Advisors on a sample of 10 years... Well, also maxima....
Even in our village any peasant, let alone a peasant... Any d@un in our county knows that a constant MO and/or variance does not guarantee that a financial instrument (or combination of them) will also have a constant MO and/or variance on the next bar... or not on the next bar, but in, say, two bars... or at least in 1 month
and you, in capitals, are even more embarrassed not to know it
and the supporters of "overoptimization once in a while" want to ask the same simple peasant question: "And what will be the criterion of overoptimization and how this criterion can be checked for non-overtraining?
Even in our village, any peasant, let alone a peasant... any d@un in our county knows that a constant MO and/or variance does not guarantee that a financial instrument (or combination of them) will also have a constant MO and/or variance on the next bar... or not on the next bar, but in, say, two bars... or at least in 1 month
and you, in capitals, should be ashamed not to know it
Nothing in this life is guaranteed. But one has to live somehow.
Nothing in this life is guaranteed. But you have to live somehow.
Are you suggesting we play Russian roulette?
Excuse me, have you read Bulgakov?
There can be many quality criteria. For synthetic it can be constant MO or variance.
If the average trade lasts 4-6 months, EXAMPLE, then the forward is 6 months. After that, the system can be over-optimized.
Fools who think that the model can "work" for a year or more without loss of quality will be punished by the market itself. It's only the morons who test advisors on a sample of 10 years... Well, also maxima....