An AutoML Algorithm: Multiple-Steps Ahead Forecasting of Correlated Multivariate Time Series with Anomalies Using Gated Recurrent Unit Networks
Open Access
Abstract
Multiple time series forecasting is critical in domains such as energy management, economic analysis, web traffic prediction and air pollution monitoring to support effective resource planning. Traditional statistical learning methods, including Vector Autoregression (VAR) and Vector Autoregressive Integrated Moving Average (VARIMA), struggle with nonstationarity, temporal dependencies, inter-series correlations, and data anomalies such as trend shifts, seasonal variations, and missing data. Furthermore, their effectiveness in multi-step ahead forecasting is often limited. This article presents an Automated Machine Learning (AutoML) framework that provides an end-to-end solution for researchers who lack in-depth knowledge of time series forecasting or advanced programming skills. This framework utilizes Gated Recurrent Unit (GRU) networks, a variant of Recurrent Neural Networks (RNNs), to tackle multiple correlated time series forecasting problems, even in the presence of anomalies. To reduce complexity and facilitate the AutoML process, many model parameters are pre-specified, thereby requiring minimal tuning. This design enables efficient and accurate multi-step forecasting while addressing issues including missing values and structural shifts. We also examine the advantages and limitations of GRU-based RNNs within the AutoML system for multivariate time series forecasting. Model performance is evaluated using multiple accuracy metrics across various forecast horizons. The empirical results confirm our proposed approach’s ability to capture inter-series dependencies and handle anomalies in long-range forecasts.Keywords
This publication has 22 references indexed in Scilit:
- Rényi entropy and divergence for VARFIMA processes based on characteristic and impulse response functionsChaos, Solitons & Fractals, 2022
- Review of ML and AutoML Solutions to Forecast Time-Series DataArchives of Computational Methods in Engineering, 2022
- Evaluation of Deep Learning Models for Multi-Step Ahead Time Series PredictionIEEE Access, 2021
- Multivariate time series forecasting via attention-based encoder–decoder frameworkNeurocomputing, 2020
- Deep Learning with Gated Recurrent Unit Networks for Financial Sequence PredictionsProcedia Computer Science, 2018
- Imputation of missing data in time series for air pollutantsAtmospheric Environment, 2015
- Modeling and prediction of Turkey’s electricity consumption using Artificial Neural NetworksEnergy Conversion and Management, 2009
- Review: A gentle introduction to imputation of missing valuesJournal of Clinical Epidemiology, 2006
- Neural network forecasting for seasonal and trend time seriesEuropean Journal of Operational Research, 2005
- Forecasting with artificial neural networks:International Journal of Forecasting, 1998