I am training an LSTM model using stock data for time series forecasting and the results are a little confusing to me. enter image description here

This is the prediction I get after 5 epochs.

enter image description here

And this after 100 epochs.

Why the prediction with 5 epochs is showing a smooth curve with lesser convergence, but for 100 epochs it is converging well with the actual values first (Before Jan 2021) and then proceeds to stray far away from the actual values (Jan 2021 period)? I trained it on a dataset with values from 2007 to 2019.


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.