1
$\begingroup$

I think this model is underfitting. Is this correct?

Model loss

Prediction vs Real

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_1 (LSTM)                (50, 60, 100)             42400     
_________________________________________________________________
dropout_1 (Dropout)          (50, 60, 100)             0         
_________________________________________________________________
lstm_2 (LSTM)                (50, 60)                  38640     
_________________________________________________________________
dropout_2 (Dropout)          (50, 60)                  0         
_________________________________________________________________
dense_1 (Dense)              (50, 20)                  1220      
_________________________________________________________________
dense_2 (Dense)              (50, 1)                   21        
=================================================================

The above is a summary of the model.
Any advice on how the model could be improved?

$\endgroup$
0
$\begingroup$

You need to include optimizer you used to make sure it is correct. By the way, your drop-out layers are not going to do anything, so you should take them away.

You likely don’t have test and train data in time-series because all data points are connected. It just has prediction value and ground truth of each period.

I recommend you use the whole dataset and rotate changing hyper-parameters of LSTM to find the best model.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.