I am currently creating a neural network(LSTM) for electrical demand forecasting and I want to include dummy variables to tell the model to treat weekdays differently from weekends, treat working hours differently from others, etc.

I am confused as to how and where in my model I can implement this.

Currently I have an input of a binary value (0 if weekday, 1 otherwise) which represents the day type of the target date.

This is concatenated directly to the output of the LSTM model and then fed to a Dense(60) layer and then this produces an output. However, it isn't working as well as I'd hope to differentiate the days.

Any help would be greatly appreciated.

  • $\begingroup$ You don't implement dummy variables in a model, you transform your categorical variables into dummy variables in your data set, before model building. $\endgroup$ – user2974951 Jul 11 at 12:54

Your Answer

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

Browse other questions tagged or ask your own question.