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.

Multivariate time series forecasting has been the focus of active research for machine learning (ML) in recent years, particularly as it is widely applied to solve supply chain and energy-related problems. However, constructing current forecasting-based models requires significant human efforts, including model construction, feature engineering and hyper-parameter tuning. Multivariate time-series data is commonly encountered in real data-driven problems, and the correlation among multivariate time series and typical time series anomalies are also discussed and addressed. Forecasting such data is more challenging due to the increase of data dimensionality and model complexity. In this article, an automated machine learning (AutoML) approach is proposed to tackle correlated multivariate time series forecasting tasks. Within the AutoML frameworks, a Recurrent Neural Network (RNN) variant, Gated Recurrent Unit (GRU) network has been empirically shown to accurately predict multivariate time series,while comparing forecasting performances with traditional statistical model Vector Autoregressive (VAR) and another AutoML model Long Short-Term Memory (LSTM).