ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting

TL;DR

This paper introduces ONE-NAS, an online neuroevolution algorithm that automatically designs and trains recurrent neural networks for real-time time series forecasting, adapting continuously to new data without pretraining.

Contribution

The paper presents the first online neural architecture search method for RNNs, enabling adaptive, real-time model updates for time series forecasting without pretraining.

Findings

Outperforms traditional statistical methods like ARIMA and exponential smoothing.

Effectively adapts to new data in real-time without pretraining.

Demonstrates superior accuracy on wind turbine and stock market datasets.

Abstract

Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance, transportation, health care, and power systems. However, real-world utilization of machine learning (ML) models for TSF suffers due to pretrained models being able to learn and adapt to unpredictable patterns as previously unseen data arrives over longer time scales. To address this, models must be periodically retained or redesigned, which takes significant human and computational resources. This work presents the Online NeuroEvolution based Neural Architecture Search (ONE-NAS) algorithm, which to the authors' knowledge is the first neural architecture search algorithm capable of automatically designing and training new recurrent neural networks (RNNs) in an online setting. Without any pretraining, ONE-NAS utilizes populations of RNNs which are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world large-scale multivariate wind turbine data as well a univariate Dow Jones Industrial Average (DJIA) dataset, and is shown to outperform traditional statistical time series forecasting, including naive, moving average, and exponential smoothing methods, as well as state of the art online ARIMA strategies.