AI RESEARCH
DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
arXiv CS.LG
•
ArXi:2509.14933v3 Announce Type: replace 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 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.