You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This model is part of a single-purpose model set.
We gain an edge by having each model dedicated to a single purpose and by using a combination of these single-purpose models, which increases the probability. (it triggers only when all models signal)
SIGNAL - Binary classification - trend/no trend
BUY/SELL - Determines the direction of the trend
SIZING
SIZING MODEL:
A model that categorizes the potential trend, with the output being a softmax category indicating the magnitude of the trend - the category is a multiple of the chunk size (e.g., 0.2%)
In other words, it confirms the trend and simultaneously indicates the probability of its magnitude. (Double confirmation). Consider creating separate models for downtrend and uptrend.
This model is part of a single-purpose model set.
We gain an edge by having each model dedicated to a single purpose and by using a combination of these single-purpose models, which increases the probability. (it triggers only when all models signal)
SIGNAL - Binary classification - trend/no trend
BUY/SELL - Determines the direction of the trend
SIZING
SIZING MODEL:
A model that categorizes the potential trend, with the output being a softmax category indicating the magnitude of the trend - the category is a multiple of the chunk size (e.g., 0.2%)
In other words, it confirms the trend and simultaneously indicates the probability of its magnitude. (Double confirmation). Consider creating separate models for downtrend and uptrend.
Output:
-2, -1, 0, 1, 2
where -2 (2* -chunk)
-1 (1* -chunk)
0 nothing
1 1chunk
2 2chunk
Design the labeling.
Vymyslet labeling
The text was updated successfully, but these errors were encountered: