Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data

TL;DR

This paper introduces the correlation recurrent unit (CRU), a new neural network architecture that performs time series decomposition within each cell and learns correlations between components, significantly enhancing forecasting accuracy.

Contribution

The paper proposes the CRU architecture that integrates decomposition and correlation learning within neural cells, advancing time-series forecasting methods.

Findings

Improved predictive performance by over 10% on multiple datasets.

CRU outperforms existing neural architectures in TSF tasks.

Effective learning of component correlations enhances forecast accuracy.

Abstract

The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to improving the predictive accuracy of TSF. Furthermore, model structures have been proposed to combine time-series decomposition methods, such as seasonal-trend decomposition using Loess (STL) to ensure improved predictive accuracy. However, because this approach is learned in an independent model for each component, it cannot learn the relationships between time-series components. In this study, we propose a new neural architecture called a correlation recurrent unit (CRU) that can perform time series decomposition within a neural cell and learn correlations (autocorrelation and correlation) between each decomposition component. The proposed neural architecture was evaluated through comparative experiments with previous studies using five univariate time-series datasets and four multivariate time-series data. The results showed that long- and short-term predictive performance was improved by more than 10%. The experimental results show that the proposed CRU is an excellent method for TSF problems compared to other neural architectures.