DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables

Time series forecasting is essential in various domains. Compared to relying solely on endogenous variables (i.e., target variables), considering exogenous variables (i.e., covariates) provides additional predictive information and often leads to more accurate predictions. However, existing methods for time series forecasting with exogenous variables (TSF-X) have the following shortcomings: 1) they do not leverage future exogenous variables, 2) they fail to fully account for the correlation between endogenous and exogenous variables. In this study, to better leverage exogenous variables, especially future exogenous variables, we propose $\textbf{DAG}$, which $\textit{utilizes $\underline{D}$ual correl$\underline{A}$tion network along both the temporal and channel dimensions for time series forecasting with exo$\underline{G}$enous}$ variables. Specifically, we propose two core components: the Temporal Correlation Module and the Channel Correlation Module. Both modules consist of a correlation discovery submodule and a correlation injection submodule. The former is designed to capture the correlation effects of historical exogenous variables on future exogenous variables and on historical endogenous variables, respectively. The latter injects the discovered correlation relationships into the processes of forecasting future endogenous variables based on historical endogenous variables and future exogenous variables.

Time series forecasting helps people make better decisions in many areas such as energy systems, traffic management, finance, and healthcare by predicting future events from historical data. In many real-world applications, forecasts can be improved by using additional information beyond the target data itself, such as weather conditions, holidays, or electricity demand. These are called exogenous variables. However, existing forecasting methods often fail to fully utilize such information, especially information that is already known about the future. They also struggle to properly model how different types of data influence one another. To address these issues, we propose a new forecasting framework called DAG. DAG is designed to better capture relationships between historical observations and external information across both time and different data sources. In simple terms, the model learns how external factors influence future outcomes and then uses these learned relationships to improve forecasting accuracy. Experiments on multiple real-world datasets show that DAG consistently produces more accurate predictions than existing methods. Our work demonstrates the importance of effectively leveraging external information for reliable forecasting in practical applications.