Machine learning in trading: theory, models, practice and algo-trading - page 3051
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
Will anything work on SB? It'll be 50/50. Well, maybe +-2% due to insufficiently large sample.
So mytarmailS claims that it will work, attaches graphs and code (which I could not run in the last version).
So mytarmailS claims that it will, attached graphs and code (which I couldn't run in the latest version).
Let him test 100 million lines. If the GCH is normal, it will be 50/50.
They don't live that long :)
I think the task should be reduced to detecting the current pattern (anomaly), which will be effective for some time, and the second part - earlier detection of the decay of this pattern/anomaly.
Not necessarily correlated. Why doesn't it make sense? I took quant segments on EURUSD and tested them on GBPUSD - about 25% showed probability bias on both pairs. What happens if you take another pair - I don't know, yet. Of course, there is a small problem - I am working with the basic signal of the strategy, and whether it should be changed on other pairs or not for this study is not clear yet. Obviously, the nature of different instruments is different. Perhaps the instruments need to be clustered at the beginning, or otherwise grouped. In general, the question of setting up the experiment is open.
Generate charts, apparently, taking into account the average descriptive statistics of a group of trading instruments. I.e. something similar in skeleton, but with random fat.
because it's also a fitting
They don't live that long :)
I think the task should be to identify a current pattern (anomaly) that will be effective for some time, and the second part is to detect the decay of this pattern/anomaly earlier.
Check 10mn. That's how many live)))
because it's also a fitting
If fitted to a large amount of data, it's already a pattern....
If fitted to a large amount of data, it's already a pattern....
No.
M1 is about 450k per year. 22 years - 10mn lines.
Check 10mn. That's how many live)))
Why take minutes at all? Do we have a signal generated on every bar? I don't know what rules he was making up there - on retournals, probably.
Either admit that there can't be any rules and everything is house and don't do it.
But if it is chaos, then no economic or more global events, such as the fall of a huge meteorite, can affect the quotes.
Perhaps, more elaborate modelling of price behaviour is required, rather than complete randomness. Let's say we take a dozen strategies and trade them as if creating quotes. From launch to launch, distribute different percentages of initial deposit to the strategies.
no
It may be a consequence, not a cause, but it's still a connected phenomenon, so as long as there is a connection, we can talk about a pattern.
We just have to recognise that laws change. And that's when they change - the moment of time - this problem should be solved.