TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

arXiv:2402.19072v1 Announce Type: new
Abstract: Recent studies have demonstrated remarkable performance in time series forecasting. However, due to the partially-observed nature of real-world applications, solely focusing on the target of interest, so-called endogenous variables, is usually insufficient to guarantee accurate forecasting. Notably, a system is often recorded into multiple variables, where the exogenous series can provide valuable external information for endogenous variables. Thus, unlike prior well-established multivariate or univariate forecasting that either treats all the variables equally or overlooks exogenous …

abstract accurate forecasting applications arxiv cs.ai cs.lg endogenous exogenous forecasting multiple nature performance series studies time series time series forecasting transformers type variables world