Temporal Window Smoothing of Exogenous Variables for Improved Time Series Prediction

2025-07-04

AI Summary

To address two key challenges in Transformer-based time-series forecasting—redundant information in exogenous variables (especially when endogenous and exogenous variables share common sources) and insufficient long-range dependency modeling—this paper proposes an exogenous variable enhancement framework featuring global statistical whitening and context-aware smoothing. First, raw exogenous variables are whitened using global mean and variance statistics to enhance sensitivity to long-term trends. Second, a lightweight temporal window smoothing mechanism is introduced to suppress local noise and redundancy without expanding the lookback horizon. The refined exogenous features are then jointly modeled with the endogenous sequence, significantly improving feature discriminability. Extensive experiments on four benchmark datasets demonstrate consistent superiority over 11 state-of-the-art baselines, validating both effectiveness and robustness.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Although most transformer-based time series forecasting models primarily depend on endogenous inputs, recent state-of-the-art approaches have significantly improved performance by incorporating external information through exogenous inputs. However, these methods face challenges, such as redundancy when endogenous and exogenous inputs originate from the same source and limited ability to capture long-term dependencies due to fixed look-back windows. In this paper, we propose a method that whitens the exogenous input to reduce redundancy that may persist within the data based on global statistics. Additionally, our approach helps the exogenous input to be more aware of patterns and trends over extended periods. By introducing this refined, globally context-aware exogenous input to the endogenous input without increasing the lookback window length, our approach guides the model towards improved forecasting. Our approach achieves state-of-the-art performance in four benchmark datasets, consistently outperforming 11 baseline models. These results establish our method as a robust and effective alternative for using exogenous inputs in time series forecasting.

Problem

• Reducing redundancy in exogenous and endogenous inputs
• Capturing long-term dependencies in time series data
• Improving forecasting with globally context-aware exogenous inputs

Innovation

• Whitens exogenous input to reduce redundancy
• Enhances long-term pattern awareness
• Maintains lookback window length efficiency