Machine learning in trading: theory, models, practice and algo-trading - page 1803
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 meaning remains - the correlation between the scales to find))))
I.e., correlation of M15 cloze with previous n minute cloze? You can resample it and see.
Yes, but I think you have to look at three scales, senior and junior. Hourly or 4x hourly in the sampling range of M15. Logic dictates)
Yes, but it seems to me it is necessary to look at three scales, senior and junior. Hourly or 4hourly in the sampling range of M15. Logic tells me)
The correlation will be high, but is there an alpha? I should check it.
I`ll put it into my RL, it will take me 5 minutes
If I do not know why I should check Metatrader, it may take more time to open (it starts to be a little glitchy after some time of use)
Well, there's something to it, not bad options you can pick up
2 years of EOC, training the last 5 months
2 years of OOS, training for the last 5 months
now to the left of OOS run 5 months, if the trend is the same... well it kind of is!
;)
and now to the left of OOS run 5 months, if the trend is the same... well it kind of is!
;)
It's already worse there, and so the 2X test period. The market statistics change all the same, there will be no perpetual motion)
there already worse, and so the 2X test period. Market statistics change all the same, there will not be a perpetual motion machine )
so it's not it (((
If your model could work both to the left and to the right of the training, it would definitely hit a certain discovered property in OHLC
but otherwise... well, like everyone else, then the task is like me - to determine that the TS is no longer working,
If i've got the statistics, i should analyze them, i don't know what's important there and how to detect that the TS has started to lose money further on, it's complicated)))
it means it's not it (((
If your model could work to the left and right of the training, you would definitely be able to hit some discovered property in OHLC
but otherwise... well, like everyone else, then the task is like me - to determine that the TS is no longer working,
If you don't know what's important and how to determine that the TS has started to lose money later on, it's complicated ))))
it will go either way... to the right it's just not clear yet)
it is more logical to do the train closer to the last data, to break later
She will go either way... on the right, she just doesn't know yet.)
That's what I'm asking - did you try the other side? She doesn't know on the left, either? - (You and I know that the chart moves to the right, don't tell her!)