Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
This work addresses the problem of improving RNNs' practicality for non-expert users in forecasting, but it is incremental as it builds on existing methods with guidelines rather than introducing a new paradigm.
The paper tackles the challenge of making Recurrent Neural Networks (RNNs) more robust and user-friendly for time series forecasting, showing through an empirical study that RNNs are competitive alternatives to established models like ETS and ARIMA in many situations.
Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition. However, established statistical models such as ETS and ARIMA gain their popularity not only from their high accuracy, but they are also suitable for non-expert users as they are robust, efficient, and automatic. In these areas, RNNs have still a long way to go. We present an extensive empirical study and an open-source software framework of existing RNN architectures for forecasting, that allow us to develop guidelines and best practices for their use. For example, we conclude that RNNs are capable of modelling seasonality directly if the series in the dataset possess homogeneous seasonal patterns, otherwise we recommend a deseasonalization step. Comparisons against ETS and ARIMA demonstrate that the implemented (semi-)automatic RNN models are no silver bullets, but they are competitive alternatives in many situations.