# Is time series multi-step ahead forecasting a sequence to sequence problem?

I'm using the keras package in order to train an LSTM for a univariate time series of type numeric (float). Performing a 1-step ahead forecast is trivial, but I'm not sure how to perform a, let's say, 10-step ahead forecast. Two questions:

1) I read about sequence to sequence NNs, but can barely find anything of it in the context of time series forecasting. Am I right with the assumption that the forecasting of more than 1 time step in advance is a seq2seq problem? That makes sense to me because each forecast depends on its predecessor.

2) An intuitive solution without seq2seq would be: Perform 1-step ahead forecast, then append this forecast to the series and use it to obtain the next forecast, and so on. How would this differ from a seq2seq approach?

• I'm still studying about seq2seq so cannot comment on the 2 points above but I would recommend that you refer below tutorial from Dr Jason Brownlee and I am sure this is what you may be looking for- machinelearningmastery.com/… Aug 9 '17 at 12:30
• 1. It can be tackled with a seq2seq model, since you have a sequence prediction problem. 2. It would suffer from an accumulation on prediction error (noise).
– Emre
Aug 9 '17 at 15:33

For example, if you have a sequence where the value is constant at each time step $x_{i+1} = x_i$, but you model learned to do $x_{i+1}=1.01x_i$ instead (which is highly likely with gradient descent algorithm). For $t=10$, the target value will be $1^{50} = 1$, however you model will predict $1.01^{50}=1.64$.