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).