1

I have a time series data of size 150. I trained 80% (120 data points) and tested the remaining 20% (30 data points) of the data set by LSTM network. So I got the predicted values of the series from 121 st to 150 th. I just used the code given in the following link.

https://www.mathworks.com/help/deeplearning/examples/time-series-forecasting-using-deep-learning.html;jsessionid=a48d67fe7e9929d7ac61cf112b9d

By using this code I am not able to forecast the future values (after 150 th) of the series. How can we do it?

Can any one please help me in this and send the matlab code ?

sameer poongadan
  • 11
  • Can you please edit the question and add the error you get while performing the operation? – Shiv Tavker May 02 '20 at 17:59
  • Thanks for your reply. I am not getting any error in the code. By using the above code we can only train and test the data. But I don't know how to forecast the future values. Here I trained first 120 points and predicted for the next 30 points (out of 150 data points). But how to predict data after 150th ( 151 onwards)? – sameer poongadan May 02 '20 at 18:46

1 Answers1

0

You can make a change in the XTest length to incorporate your "151 onwards points".

Note that you can no longer evaluate the error as your labeled data gets over by 150 points. You can just get YPred. You will have to figure out the syntax.

Please consider asking such questions on CS Stack Exchange or StackOverflow.

Shiv Tavker
  • 1,612
  • 7
  • 19