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?

$\endgroup$
1
  • $\begingroup$ I'd recommend renaming the Question Title to "Is this LSTM model underfitting?" rather than "Is this Keras LSTM model underfitting?" because there is nothing specific to keras in this question. $\endgroup$ Aug 28, 2021 at 2:06

1 Answer 1

1
$\begingroup$

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.

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .