Machine learning in trading: theory, models, practice and algo-trading - page 2132
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 just put the time and day of the week and the color of the candle...
data as a separate week, forty weeks in all, and within them searched for patterns
Friday_18:20_dw means Friday - 18:20 - falling candlestick
confidence - percentage of rule 1 working is 100%
count - how many of such rules were found
this rule
it means, if on Thursday at 1AM there was a rising candle, on Friday at 6:20 PM it will be falling. 20 rules were found, and the rule has worked 20 times out of 20 found
IDD...
you can add more harmonic minutes, and sum up the sinusoids, you get one curve to describe the three signs
But what to do and weekends and holidays, you need to take it all into account, what the hell is it all for?This is just a general picture.
And weekends (Saturday, Sunday) are not involved at all.
I tried my own metric , but it only works for SL=TP, for other ratios you have to count Hearst.
clearly
Run them for the next 40 weeks.
the funny thing is i don't have any more))
it's just a test of an approach, an approach that does not try to predict the next candle, but tries to find the pattern first
not participate at all.
I meant on holidays.
For example - Thursday, it's a holiday, the market is closed, and the dumb harmonica is drawing a curve
That's why the results are different for the guys here)
meant holidays
Holidays can be excluded from consideration. And define processing rules for holidays.
This is just a general picture.
And weekends (Saturday, Sunday) are not involved at all.
Holidays can be excluded from consideration. And for holidays we can define the rules for processing.
everything is possible, the question is why
Depending on the time zone, it can cling to the beginning of Saturday or the end of Sunday.
Yes, there is such a thing. But for such cases, you can make adjustments to account for these shifts.
anything is possible, the question is why.
I'm talking about the fundamental possibility of such a representation.
The question "why?" -- that's a different question.
I'm thinking of doing a "full search" of regularities, without a target like "what will happen on the next candle" and the like...
Search consists in the fact that I will look for just regularities, the target is to find a pattern, and not "what will be on the next candle", also regularities can be stretched in time, for example, if today was "event 1" and then "event 2" For example, if today there was "event 1" and then "event 2", and then " event 3", then tomorrow at 14:05 there will be a rising candle, something like that))
I have a better idea of how it should look like, and what algorithm to apply, but I would probably need some computing power, which I don't have (
By the way a question, how many repetitions of an event to consider it a pattern?
3 is already a pattern, it may be random. It is better to summarize and at a set of, say, more than 3% to sift out those less than 2%. And then increase and then analyze. If all repetitions are less than 1% there is no pattern. If there are repetitions of more than 10% then there is a pattern. We should also take into account the regularity. Regular rare repetitions are better than frequent random ones.