Machine learning in trading: theory, models, practice and algo-trading - page 1358
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 work for 1m. In 3 months, 55k OHLSV. What kind of history would I need if I went to 1h, or at least 15m? And so I have 3 months, well 6 months. for everything - about everything.
Further, for 5-10 m unlikely that something drastic will happen, and even will - we react. And in an hour, very likely there will be an event, which may not be detected at once, but in the aftermath may disrupt the "planned" course of events. Well, and there is no pattern that you were beginning to count on - dissolved.
In general, my concept - to predict anything at long intervals is unrealistic. Classification, especially a priori, is the same prediction. And the same type of events will not be enough for classification.
Tell me what to do with it in terms of strategy. If the forecast goes for every bar, every third one is wrong, and we will enter by the first one after closing the deal, then how to control the situation here - isn't there too much randomness? I now know the points, in which the decision will be made - to enter the market or not, I think it is necessary to look for such points, so that at least there would be some stationarity ....
Tell me what to do about it, in terms of strategy. If the forecast goes for every bar, every third one is wrong, and we will enter by the first one after closing the deal, then how to control the situation here - isn't there too much randomness? I now know the points, in which the decision will be made - to enter the market or not, I think it is necessary to look for such points, so that at least there would be some stationarity....
I do not understand the question. I mean that on large TF no enough history, and within the candle is quite probable a number of events that will break your entire deal and all of your patterns. On small TF this probability is insignificant.
I have 10-15 events per day on the 1F. 4-5 of them I will definitely realize. Well, and I build similar strategies.
The concept is simple. Came - look for entry into the transaction. In - immediately begin to look for an exit. If I came out - look for the entrance to the next one.
I don't understand the question.
I have 10-15 events a day on 1m. Four or five of them I'm sure to implement. Well, and I build similar automata.
The concept is simple. You came - look for entry into the transaction. In - immediately begin to look for the exit. Came out - look for the entrance to the next one.
What about the direction? My direction is clearly determined by the vector of motion now ZZ. And then how do you calculate the exit - I have a trawl.
I'm talking about the signal to enter through the "Do not go in" bar - should I react to this "Do not go in" by closing or ignore it? If you react, then I think it will be a very twitchy trade... If I ignore it, it will be unbiased in relation to the model.
What about the direction? My direction is clearly determined by the vector of motion now ZZ. And then, how do you implement the exit - I have a trawl.
And I'm talking about the signal to enter, through the bar "do not enter" - to this "do not enter" react to close, or ignore? If you react, I think it will be a very twitchy trade... If I ignore it, it will be very unbiased in relation to the model.
Direction. We enter when the movement is confirmed and there is potential for development. Exit when the movement ends or starts in the other direction (and it does not matter whether it does or does not), trawl for sharp fluctuations. Flips? - What's the point? Late for what?
If there's a reason, we react; if not, we don't react. Make a mistake, fine, get out. Twitchy? Ask the potato seller at the market, what's his trade? - (He's a jittery one.) But with us - 5 - 10, well, 15 transactions a day - just quiet.) If you miss it, the next one will be for you.)
In general, elements of indifference in trade should be. You can't make all the money anyway.)Direction. Enter when the movement is confirmed and there is potential for development. Exit when the movement ends or starts in the other direction (and it doesn't matter if it does or doesn't), trawl for sharp swings. Flips? - What's the point? Late for what?
If there's a reason, we react; if not, we don't react. Make a mistake, fine, get out. Twitchy? Ask the potato vendor at the market, what's his trade? - (He's a jittery one.) But with us - 5 - 10, well, 15 transactions a day - just quiet.) If you miss it, it doesn't matter. There'll be another one.)
I used to make 100-500 deals a day.
Normal people have 100-500 deals a day.
We don't give a shit who has how many.) Go to the normal, what are you doing here?
I watched the video (Saveliev S.V.). Everything is normal, there is nothing new globally, but denial of compensation by the brain of the damaged fields (zones) has caused bewilderment, this phenomenon was studied by Luria on concrete people, and besides he in the beginning confirms that neural connections are constantly formed, as well as all accompanying tissues. In general, a man with his own position, which was formed long ago and is now monetized. Talking about psychology out of his mouth seemed to be a bit sweeping. But I would read his popularized book "Morphology of Consciousness" for a small fee, I just wonder, if there is something new there...
If you are interested in neuropsychology - read the textbook"Neuropsychology: Textbook for Higher Education."Chomskaya E.Direction. Enter when the movement is confirmed and there is potential for development. Exit when the movement ends or starts in the other direction (and it doesn't matter if it does or doesn't), trawl for sharp swings. Flips? - What's the point? Late for what?
If there's a reason, we react; if not, we don't react. Make a mistake, fine, get out. Twitchy? Ask the potato vendor at the market, what's his trade? - (He's a jittery one.) But with us - 5 - 10, well, 15 transactions a day - just quiet.) If you miss it, there will be another one.)
In general, elements of indifference in trade should be. (You will not make all the money anyway.)And how do you measure the confirmation of the movement, and especially the development potential? Well, let's say the potential can be defined by some conditional resistance levels / breakpoints - even if the same strike is near. I don't understand what the model is responsible for. In my case it is just a x-point movement forecast with CatBoost, it is almost a regression.