Foundations of Sequence-to-Sequence Modeling for Time Series

05/09/2018

∙

by   Vitaly Kuznetsov, et al.

∙

Google

∙

MIT

∙

0

∙

share

The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forecasting framework. We include a comparison of sequence-to-sequence modeling to classical time series models, and as such our theory can serve as a quantitative guide for practitioners choosing between different modeling methodologies.