Machine learning in trading: theory, models, practice and algo-trading - page 1720

[Rorschach]

Maxim Dmitrievsky:

Thanks for the link )) I was just looking for something about natural cycles

Dependence of hourly increments with a lag of 24 on the previous one with the same lag, for example. I.e. looking at the previous one and predicting the current one

This works as long as the average increment deviates from zero (say, a sample of a year). There buying or selling accordingly. The articles have it all.

The reason for dividing by daily increments is clear. The American session is one process, the European one and so on. In other words, we regard the current European session as a continuation of yesterday's session, a specific hour or several hours, cutting out the rest.

Monthly cycles are also more or less clear. As for the rest, I do not know.

I tried to do the same for cointegrated (conditional) instruments, to improve cointegration, to take by hours. Better than the whole series, but uninspired.

With kotir it is clear, but why does it work on random...

By the way, I kind of did something like that, I was counting the probability of candle direction at a certain time of day and I didn't find anything interesting.

From all remembered round levels and cycles, but 10% on the background of "noise" how to use this. By the way, surprised by the existence of the cycle of 2.5 days, long change the settings, but the cycle seems to be real.

[Maxim Dmitrievsky]

Rorschach:

With kotir is clear, but why does it work on random...

Fz, let someone else check, maybe I'm lying... but the method is the same

[mytarmailS]

There are no cycles, calm down already.

[Maxim Dmitrievsky]

mytarmailS:
There are no cycles, calm down already.

Did you check? ) And if I do?

[mytarmailS]

Maxim Dmitrievsky:

have you checked? ) And if I do?

sure)

[Rorschach]

I'm a handicapper, the RNG is broken((((

#include <Canvas\Canvas.mqh>
void OnStart()
  {CCanvas C;
   int h=1024;
   int w=2048;
   C.CreateBitmapLabel("11",100,100,w,h);
   for(int y=0;y<h;y++)
     {//srand(GetMicrosecondCount());
      for(int x=0;x<w;x++)
        {uchar c=0;
         for(int k=0;k<16;k++)
           {c=uchar(255.*rand()/32767.);
           }
         C.PixelSet(x,y,ARGB(255,c,c,c));
        }
     }
   C.Update();

Way 1: w must be a power of 2, k is a multiple of 4

Way 2: uncomment srand

Method 2 should also work on the Mersen vortex

[mytarmailS]

Fellas, who knows how you can make a series of stationary along with the trend?? How with the distribution to play or boxes coxes there all? or any ideas?

Or there is only one option here, to separate the trend and the "rest" If we want the "rest" to be stationary, we should forecast the trend separately.

Who has a good idea about it?

[Maxim Dmitrievsky]

I, says your econometrics.... back in kindergarten.... and I didn't choke on it.

[Дмитрий]

mytarmailS:

Guys, who knows how you can make a series of stationary along with the trend??? How with the distribution to play or boxes coxes there all? or any ideas?

Or there is only one option here, to separate the trend and the "rest" If we want the "rest" to be stationary, we should forecast the trend separately.

Who knows a lot about it?

The only way to make them stationary is to detrend a series.

Well, this is if to study the whole series without throwing out chunks and thinning.

[mytarmailS]

Dmitry:

The only way to make it stationary is by detrending the series.

Well, this is if you study the whole series, without throwing out chunks and thinning

Thank you, but that is exactly the way I described.

mytarmailS:

Or there is only one option here, to separate into a trend and "the rest" The "rest" is stationary and the trend is predicted separately

An econometrician would do exactly that, but we all know it won't work for the quotes, although it seems to have been created for such tasks)

After such transformations with new data the MO dies almost immediately, I am more interested in any ideas, alternatives, thoughts on why it happens, etc.....

Maxim Dmitrievsky:

I, says your econometrics.... back in kindergarten.... and I didn't choke on it.

Oh Sensei, tell me and all of us what econometric transformations can make the series stationary, you know we are all dumb, rub your ego, come on, come on we are all waiting