Time Series Forecasting With Deep Learning: A Survey
This is an incremental survey paper summarizing existing methods for researchers and practitioners in time series analysis.
The paper surveys deep learning architectures for time series forecasting, covering encoder-decoder designs, hybrid models combining statistical and neural approaches, and decision support applications.
Numerous deep learning architectures have been developed to accommodate the diversity of time series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time series forecasting -- describing how temporal information is incorporated into predictions by each model. Next, we highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. Lastly, we outline some ways in which deep learning can also facilitate decision support with time series data.