Model identification for ARMA time series through convolutional neural networks

TL;DR

This paper demonstrates that convolutional neural networks can accurately and rapidly identify ARMA models from time series data, outperforming traditional likelihood-based methods in both accuracy and speed.

Contribution

The study introduces neural network-based methods for ARMA model identification, showing significant improvements over traditional likelihood-based criteria.

Findings

Neural networks outperform likelihood methods in accuracy.

Neural networks are much faster than traditional methods.

CNNs effectively identify ARMA models from simulated data.

Abstract

In this paper, we use convolutional neural networks to address the problem of model identification for autoregressive moving average time series models. We compare the performance of several neural network architectures, trained on simulated time series, with likelihood based methods, in particular the Akaike and Bayesian information criteria. We find that our neural networks can significantly outperform these likelihood based methods in terms of accuracy and, by orders of magnitude, in terms of speed.