How Much Can Time-related Features Enhance Time Series Forecasting?

TL;DR

This paper introduces TimeSter, a simple module for encoding time-related features in time series forecasting, which significantly improves accuracy and efficiency, especially when combined with a linear backbone.

Contribution

The paper proposes TimeSter, an efficient encoding module for time-related features, and demonstrates its effectiveness when integrated with a linear model for improved forecasting.

Findings

TimeSter enhances forecasting accuracy by capturing cyclical patterns.

TimeLinear reduces MSE by 23% on benchmark datasets.

The approach maintains high efficiency with fewer parameters.

Abstract

Recent advancements in long-term time series forecasting (LTSF) have primarily focused on capturing cross-time and cross-variate (channel) dependencies within historical data. However, a critical aspect often overlooked by many existing methods is the explicit incorporation of \textbf{time-related features} (e.g., season, month, day of the week, hour, minute), which are essential components of time series data. The absence of this explicit time-related encoding limits the ability of current models to capture cyclical or seasonal trends and long-term dependencies, especially with limited historical input. To address this gap, we introduce a simple yet highly efficient module designed to encode time-related features, Time Stamp Forecaster (TimeSter), thereby enhancing the backbone's forecasting performance. By integrating TimeSter with a linear backbone, our model, TimeLinear, significantly improves the performance of a single linear projector, reducing MSE by an average of 23\% on benchmark datasets such as Electricity and Traffic. Notably, TimeLinear achieves these gains while maintaining exceptional computational efficiency, delivering results that are on par with or exceed state-of-the-art models, despite using a fraction of the parameters.