Machine learning in trading: theory, models, practice and algo-trading - page 3550

New comment
 
Maxim Dmitrievsky #:
I'm chillin'. It's gotten worse. Basically if you subtract the return with any lag from the prices, you get roughly the same model. So you're just taking something away from the original prices.
No magic happens.
I'm telling you for the third and final time)))
Do exactly what I did, instead of making up your own incomprehensible things... and then you make wrong conclusions based on it.
 
mytarmailS #:
I'm telling you for the third and last time.)
Do exactly what I did, not your own not understandable what... and then based on this you make wrong conclusions
Where are your conclusions? At least make a backtest :)
The conclusions are unambiguous. It is enough to take any differentiated series and subtract it from the original one. This is the inverse operation of integrating the signs into the original series.
 
Maxim Dmitrievsky #:
Where are your conclusions? At least do a backtest :)
The conclusions are unambiguous. It is enough to take any differentiated series and subtract it from the original one. This is the inverse operation of integrating the signs into the original series.

A backtest is when you already have a complete robot.

Ohh. Okay.

all by myself, all by myself.

 
mytarmailS #:

a backtest is when there's already a full-fledged robot.

Ohh. Okay.

all by myself, all by myself.

I tested the full-fledged one, it got worse.
Why it is similar to your TS - I will not explain, it will take a lot of energy, and I am on the chill :).

In brief, I use these models to mark trades, just like you take signals from them.
 
Maxim Dmitrievsky #:
In short, I use these models to place trades, just like you take signals from them.
Yeah, except we have different models, but you think we're the same.
 
mytarmailS #:
Yeah, except we have different models, but you think they're the same.
Yeah, I've had a few. Mashka + returnee, no short mashka, a few returnees. All worse. But it works on new data, but not very well.
 
Maxim Dmitrievsky #:
Yeah, I've gone through a few. Mashka + returnee, no short mashka, a few returnees. Everything is worse. But it works on new data, but not very well.
There patern should be done on model candlesticks, you didn't do that or even candlesticks
 
mytarmailS #:
You have to make a paternion on the model candles, you didn't do that and you didn't even make candles.
I didn't do that, I just kind of finessed it.
 

Wrote a monster that builds 2 level clustering and looks for profitable clusters.

Finds all sorts of interesting TCs


 

The log is just as inadequate. You can see that he finds either a good TC or nothing :)

Iteration: 0, Cluster: 0, SubCluster: 0
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 0, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 0, SubCluster: 2
R2: 0.9628026860906548
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 0, Cluster: 1, SubCluster: 0
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 1, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 1, SubCluster: 2
R2: 0.9804180988990353
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 0, Cluster: 2, SubCluster: 0
R2: 0.9930599292110455
Iteration: 0, Cluster: 2, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 2, SubCluster: 2
R2: 0.9703596382909541
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 0, Cluster: 3, SubCluster: 0
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 3, SubCluster: 1
R2: 0.977346448254901
Iteration: 0, Cluster: 3, SubCluster: 2
R2: 0.9624951019356504
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 0, Cluster: 4, SubCluster: 0
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 4, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 0, Cluster: 4, SubCluster: 2
R2: 0.8132121850814286
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 1, Cluster: 0, SubCluster: 0
R2: 0.9440795561361571
Iteration: 1, Cluster: 0, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 1, Cluster: 0, SubCluster: 2
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 1, Cluster: 1, SubCluster: 0
R2: 0.9473495554472346
Iteration: 1, Cluster: 1, SubCluster: 1
R2: 0.983402942661654
Iteration: 1, Cluster: 1, SubCluster: 2
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 1, Cluster: 2, SubCluster: 0
R2: 0.9656292626281533
Iteration: 1, Cluster: 2, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 1, Cluster: 2, SubCluster: 2
R2: 0.9693720703907486
Too few samples in subcluster: 0
Too few samples in subcluster: 0
Iteration: 1, Cluster: 3, SubCluster: 0
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
Iteration: 1, Cluster: 3, SubCluster: 1
/Users/dmitrievsky/miniforge3/lib/python3.10/site-packages/sklearn/metrics/_regression.py:1187: UndefinedMetricWarning: R^2 score is not well-defined with less than two samples.
  warnings.warn(msg, UndefinedMetricWarning)
R2 is fixed to -1.0
R2: -1.0
1...354335443545354635473548354935503551355235533554355535563557...3586
New comment