Recurrent Neural Networks for Time Series Forecasting

TL;DR

This paper introduces a comprehensive RNN-based framework for time series forecasting, including feature engineering, importance analysis, and evaluation, supported by empirical studies with LSTM and GRU models.

Contribution

It presents a novel, integrated framework for time series forecasting using RNNs, covering multiple aspects from feature processing to evaluation.

Findings

LSTM and GRU models effectively forecast time series data.

Feature importance analysis enhances model interpretability.

The framework improves forecasting accuracy over baseline methods.

Abstract

Time series forecasting is difficult. It is difficult even for recurrent neural networks with their inherent ability to learn sequentiality. This article presents a recurrent neural network based time series forecasting framework covering feature engineering, feature importances, point and interval predictions, and forecast evaluation. The description of the method is followed by an empirical study using both LSTM and GRU networks.