Machine learning in trading: theory, models, practice and algo-trading - page 2136
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
Of course it is possible, but we need to set the task correctly
Well, let Alexander give a file with ticks (I think he has unfiltered ones) and describe the criteria that should be met by the thinned series.
Why cram dozens of MO indicators for training if you can teach by points in space (patterns). The program will produce error-free solution.
I've explained to you what an indicator is, with colors like a child, and you keep stirring the same stuff.
If you know how to make error-free decisions, why do you need ME?
Well, let Alexander give you a file with ticks (I think he has unfiltered ones) and describe the criteria that a thinned series should meet.
I'm not interested in it ...
You don't understand what an indicator is, or rather a filter...
An indicator is a mathematical formula (filter) that transforms the original information into something of higher quality (filtered)
When drawing a trend line from extremums to filter an event, you create a mathematical transformation(filter)== indicator
And right after that you shout out from your lack of understanding that it doesn't work))) Paradox)
More precisely the problem of stereotypical thinking ...
DOT))
Scientific formulas will not bring you any closer to success.)
You have to understand the market to do that.
Here is the point.
Scientific formulations won't get you any closer to success.)
You have to understand the market to do that.
That's the point.
These are not scientific formalisms, but generally accepted concepts...
It's necessary that people speak the same language, then and only then there's a chance that they understand each other...
A market model cannot be built based on indicator readings.
A model can only be built by the position of points in space.
In our case, by the position of points on the chart plane.
Indicators are created to describe the state of the market by highlighting important information, according to the opinion of the creator of the indicator. If the information it highlights, sometimes through transformation, is really important for market participants, then the indicator will improve the trading model (not the market model).
In general, I don't understand why you suddenly decided that I use only indicators, as I understood oscillators. In my article I have shown that the indicators from standard delivery can be useful, do you deny it?
A market model cannot be built based on indicator readings.
A model can only be built by the position of points in space.
In our case, by the position of points on the chart plane.
This is an incorrect and contradictory opinion.
Who says that the points on the chart cannot be the indicator points?
By the way, the most useful indicators are the ones that structure the chart surface.
Wrong and contradictory opinion.
Who says that the points on the chart cannot be indicator points?
By the way, the most useful indicators are those that structure the chart surface.
And what is that supposed to mean?
In fact, all that needs to be predicted is the velocity of the upper and lower trendlines built from the last two extrema,
By the velocity it is possible to construct (extrapolate) the predicted trend rays
Indicators are created to describe the state of the market by highlighting important information, according to the creator of the indicator. If the information it highlights, sometimes through transformation, is really important for market participants, then the indicator will improve the trading model (not the market model).
In general, I don't understand why you suddenly decided that I use only indicators, as I understood oscillators. In my article I showed that the indicators from the standard delivery can be useful, do you deny it?
No. I don't deny the usefulness of indicators, even oscillators. But you can't build a machine model on them that will take into account the real price change in pips. This is important in making a decision to buy or sell. The signal will be there. But the longevity is under a big question.
A market model must be built at specific prices and times. Machine recognition implies a characteristic in the form of price, not a time-blurred derivative of it.
Wrong and contradictory opinion.
Who says that points on a chart can't be indicator points?
By the way, the most useful indicators are those that structure the chart surface.
That is absolutely correct. The chart itself is the indicator of price changes.
I'm just saying that for the MO it's more profitable to use aprice point in time than the fog of some makdi or stochastic.
In fact, all that needs to be predicted is the speed of the upper and lower trendline from the last two extrema,
you can plot (extrapolate) the predicted trend rays by the velocity
I've lost interest in talking to you.))