Are CNNs good for time series?

CNNs don’t have the assumption that history is complete: Unlike RNNs, CNNs learn patterns within the time window. If you have missing data, CNNs should be useful . In a way, CNNs can look forward: RNN models only learn from data before the timestep it needs to predict.

Read more

What is grouped time series?

Grouped time series involve more general aggregation structures than hierarchical time series . With grouped time series, the structure does not naturally disaggregate in a unique hierarchical manner, and often the disaggregating factors are both nested and crossed.

Read more

What is N Beats?

N-beats is a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers . The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train.

Read more