LSTMs are widely used for sequence prediction problems and have proven to be extremely effective . The reason they work so well is that LSTM can store past important information and forget the information that is not.
Read moreIs RNN good for time series?
The good performance of the Vanilla RNN, which does not integrate the “long” aspect of the LSTM algorithm, implies that the time series follows a pattern that does not require much of a long-term memory.
Read more