Model identification for ARMA time series through convolutional neural networks

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Wai Hoh Tang, Röllin, Adrian
Format: Article
Language:English
Subjects:
Artificial neural networks
Autoregressive models
Autoregressive moving average
Autoregressive moving-average models
Bayesian analysis
Computer simulation
Neural networks
Time series
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422