In this paper, we present a new approach to time series forecasting. Time
series data are prevalent in many scientific and engineering disciplines. Time
series forecasting is a crucial task in modeling time series data, and is an
important area of machine learning. In this work we developed a novel method
that employs Transformer-based machine learning models to forecast time series
data. This approach works by leveraging self-attention mechanisms to learn
complex patterns and dynamics from time series data. Moreover, it is a generic
framework and can be applied to univariate and multivariate time series data,
as well as time series embeddings. Using influenza-like illness (ILI)
forecasting as a case study, we show that the forecasting results produced by
our approach are favorably comparable to the state-of-the-art.
Description
Deep Transformer Models for Time Series Forecasting:The Influenza Prevalence Case - 2001.08317.pdf
%0 Generic
%1 wu2020transformer
%A Wu, Neo
%A Green, Bradley
%A Ben, Xue
%A O'Banion, Shawn
%D 2020
%K deeplearning timeseries todo:read transformer
%T Deep Transformer Models for Time Series Forecasting: The Influenza
Prevalence Case
%U http://arxiv.org/abs/2001.08317
%X In this paper, we present a new approach to time series forecasting. Time
series data are prevalent in many scientific and engineering disciplines. Time
series forecasting is a crucial task in modeling time series data, and is an
important area of machine learning. In this work we developed a novel method
that employs Transformer-based machine learning models to forecast time series
data. This approach works by leveraging self-attention mechanisms to learn
complex patterns and dynamics from time series data. Moreover, it is a generic
framework and can be applied to univariate and multivariate time series data,
as well as time series embeddings. Using influenza-like illness (ILI)
forecasting as a case study, we show that the forecasting results produced by
our approach are favorably comparable to the state-of-the-art.
@misc{wu2020transformer,
abstract = {In this paper, we present a new approach to time series forecasting. Time
series data are prevalent in many scientific and engineering disciplines. Time
series forecasting is a crucial task in modeling time series data, and is an
important area of machine learning. In this work we developed a novel method
that employs Transformer-based machine learning models to forecast time series
data. This approach works by leveraging self-attention mechanisms to learn
complex patterns and dynamics from time series data. Moreover, it is a generic
framework and can be applied to univariate and multivariate time series data,
as well as time series embeddings. Using influenza-like illness (ILI)
forecasting as a case study, we show that the forecasting results produced by
our approach are favorably comparable to the state-of-the-art.},
added-at = {2021-04-28T08:19:04.000+0200},
author = {Wu, Neo and Green, Bradley and Ben, Xue and O'Banion, Shawn},
biburl = {https://www.bibsonomy.org/bibtex/24a3943735d80f2993dbfa12893a0bf63/annakrause},
description = {Deep Transformer Models for Time Series Forecasting:The Influenza Prevalence Case - 2001.08317.pdf},
interhash = {d401ed302fafa94adc07bf47aae1066d},
intrahash = {4a3943735d80f2993dbfa12893a0bf63},
keywords = {deeplearning timeseries todo:read transformer},
note = {cite arxiv:2001.08317Comment: 10 pages, 7 figures},
timestamp = {2021-04-28T08:19:04.000+0200},
title = {Deep Transformer Models for Time Series Forecasting: The Influenza
Prevalence Case},
url = {http://arxiv.org/abs/2001.08317},
year = 2020
}