Autoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction
This work addresses the complex problem of time series prediction for domains requiring multivariate analysis, though it appears incremental as it builds on existing architectures.
The authors tackled time series forecasting by proposing a hybrid model combining convolutional layers, a recurrent encoder, and a linear autoregressive component, which outperformed baselines in multivariate datasets with up to 50% improvement in some cases.
Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a recurrent encoder and a linear autoregressive component. We motivate the model and we test and compare it against a baseline of widely used existing architectures for univariate and multivariate timeseries. The proposed model appears to outperform the baselines in almost every case of the multivariate timeseries datasets, in some cases even with 50% improvement which shows the strengths of such a hybrid architecture in complex timeseries.