Improving the accuracy of global forecasting models using time series data augmentation

作者：

Highlights：

• Time series data augmentation techniques for global forecasting models.

• Importing time series domain knowledge using pooled and transfer learning approaches.

• Improving the accuracy of baseline global forecasting models.

摘要

•Time series data augmentation techniques for global forecasting models.•Importing time series domain knowledge using pooled and transfer learning approaches.•Improving the accuracy of baseline global forecasting models.

论文关键词：Time series forecasting,Global forecasting models,Data augmentation,Transfer learning,RNN

论文评审过程：Received 6 August 2020, Revised 20 December 2020, Accepted 30 June 2021, Available online 9 July 2021, Version of Record 16 July 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108148