Machine learning in trading: theory, models, practice and algo-trading - page 304
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
Actually, we have no data on which the price and its changes depend. And it can't be, unless we are insiders. In general, we are looking for indirect (secondary) data about the future in the price behavior itself. That is, our data depends precisely, on the price and its behavior in the past and present.
And this statement:you should predict the price with data from which it changes. You cannot agree with it. Well, it is indisputable that the higher the quality of input forecasts is, the better the results are.
------------------------------
So, I have to combine different IDEs for different tasks and transfer data between them. Too bad. I wanted to do everything better (on R) and it turned out to be the same as always.
My dear fellow, you are really something else. The subject area should know thoroughly, and not only consider the quotient as a non-stationary time series, in the market is involved who????. People, machines, they do what? Transactions, transactions form volume and delta, which is what moves the price. Let me tell you a secret, only you don't tell anyone!!!!! In my article attached "Sequenta" for MT5 take its signals and build the delta profile in the window, no NS is needed there. Of course it's not that simple, that's why you have to use NS, but such data actually exists, there is also cheating on the part of the market, do you think it's that simple? After all, this information is available to everyone.
The formation of prices in the market is carried out in a strict sequence. The formation of the volume (Delta) - price change - change of the indicator. This is the sequence of market operation. But do not think that you can win in time, because the information about the volume comes later than the price, but it's not important when working on a longer interval, when the information obtained is generalized. For example, I use the SPSP pattern and if it appears in the "Sequents" window, you don't need to ask a babylike question :-)
Really, the development environment can be any, but no one canceled the rules of data collection, you need to make a careful and clean selection of data and think about the output.
You're really something, you know? You need to know the subject area thoroughly, and not just consider the quotient as a non-stationary time series, in the market involved who????. People, machines, they do what? Transactions, transactions form volume and delta, which is what moves the price. Let me tell you a secret, only you don't tell anyone!!!!! In my article attached "Sequenta" for MT5 take its signals and build the delta profile in the window, no NS is needed there. Of course it's not that simple, that's why you have to use NS, but such data actually exists, there is also cheating on the part of the market, do you think it's that simple? After all, this information is available to everyone.
The formation of prices in the market is carried out in a strict sequence. The formation of the volume (Delta) - price change - change of the indicator. This is the sequence of market operation. But do not think that you can win in time, because the information about the volume comes later than the price, but it's not important when working on a longer interval, when the information obtained is generalized. For example, I use the SPSP pattern and if it appears in the "Sequents" window, you don't need to ask a babylike question :-)
Indeed, the development environment can be any, but no one canceled the rules of data collection, you need to carefully make a clean selection of data and think about the output.
Subject area, you say? I've been studying the application of volumes to forecasting. The correlation with price movement is obvious, but volumes do not provide any additional information compared to price alone. They rather increase the level of noise in the system. Of course we are talking about the time intervals on which the research has been conducted.
Of course I do not plan to repeat or even use any Sequent and SanSanych systems. But I will definitely take some methodological developments.
For example, in his article, SanSanych showed learning with a derivative of ZigZag, shifting it to the left. Imho, a very good example of system learning. However, it should be shifted to the place where predictors used in the system predict the price movement, i.e. to the place where the trade should actually be executed. Perhaps not the ZigZag. But it is still a long way off).
A subject area, you say? I studied the question of using volumes for forecasting. The correlation with price movement is obvious, but volumes do not provide any additional information compared to using only price. They rather increase the level of noise in the system. Of course we are talking about the time intervals on which the research has been conducted.
Of course I do not plan to repeat or even use any Sequent and SanSanych systems. But I will definitely take some methodological developments.
For example, in his article, SanSanych showed learning with a derivative of ZigZag, shifting it to the left. Imho, a very good example of system learning. However, it should be shifted to the place where predictors used in the system predict the price movement, i.e. to the place where the trade should actually be executed. Perhaps not the ZigZag. But it is still a long way off).
Well, yes, Zig Zag can be used to exit, but very carefully. You mentioned volumes, I was talking about Delta, I think it will be more important than volumes.
Well yes, Zig Zag can be used to exit, but very carefully. You mentioned volumes, I was talking about Delta, which I think is more important than volumes.
Let's clarify the terminology. What is Delta?
Well, yes, the ZigZag, I suppose, cannot be used at all. Unless in training, as in SanSanych's article, with some restrictions.
Let's clarify the terminology. What is Delta?
Well, yes, the ZigZag, I suppose, cannot be used at all. Unless in training, as in SanSanych's article, with some restrictions.
Delta is the difference between buyers and sellers, in other words says who had more buyers or sellers in the current hour.
Delta is the difference between buyers and sellers, in other words says who had more buyers or sellers in the current hour.
I don't understand it. In the market there is always an equal number of buyers and sellers. Equality - how much is bought, exactly as much is sold is unconditionally fulfilled.
Whoa, whoa, whoa, what are you talking about? Where is this coming from? The data is taken from the real CME exchange, where the number of buyers and sellers is not always equal. Look at this project and read it first to reason adequately. I'm Shiseyu.... and this on the most popular trading forum :-)))))
In the market there is always an equal number of buyers and sellers. Equality - as much is bought and as much is sold.
What are you talking about? Where is this coming from? The data is taken from the real CME exchange where the number of buyers and sellers is not always equal. Look at this project and read it first to reason adequately. I'm Shiseyu.... and this on the most popular trading forum :-)))))
I don't see the connection. I am aware of the information exchanges give.
Once again, how much is bought, how much is sold, and so on in the pre-post. So what exactly do you mean by your statement?
In general, this is not the subject of the MO, let's talk about it somewhere else.
You seem to trade on the stock exchange, but you're so dense.)