.png){kind=icon}
.png){kind=icon}
Return
A multi-task encoder-dual-decoder framework for mixed frequency data prediction
.png){kind=icon}
OA
AI
DOI：10.1016/j.ijforecast.2023.08.003.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Mixed -frequency data prediction tasks are pertinent in various application domains, in which one leverages progressively available high -frequency data to forecast/nowcast the low -frequency ones. Existing methods in the literature tailored to such tasks are mostly linear in nature; depending on the specific formulation, they largely rely on the assumption that the (latent) processes that govern the dynamics of the high- and low -frequency blocks of variables evolve at the same frequency, either the low or the high one. This paper develops a neural network -based multi -task shared -encoder -dual -decoder framework for joint multi -horizon prediction of both the low- and high -frequency blocks of variables, wherein the encoder/decoder modules can be either long shortterm memory or transformer ones. It addresses forecast/nowcast tasks in a unified manner, leveraging the encoder-decoder structure that can naturally accommodate the mixed -frequency nature of the data. The proposed framework exhibited competitive performance when assessed on both synthetic data experiments and two real datasets of US macroeconomic indicators and electricity data. (c) 2023 The Authors. Published by Elsevier B.V. on behalf of International Institute of Forecasters. This is an open access article under the CC BY -NC -ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keywords:
Mixed-frequency data
Encoder-decoder
LSTM
Transformer
Multi-horizon forecasts
Nowcasting
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.1
Papers:
3.1K
Citations:
9.9K
