Predicting the Future by Retrieving the Past

TL;DR

This paper introduces PFRP, a method that improves univariate time series forecasting by explicitly retrieving and integrating global historical patterns through a memory bank, significantly boosting accuracy.

Contribution

The paper presents a novel global memory bank and retrieval mechanism to explicitly incorporate global historical data into forecasting models, enhancing their performance.

Findings

PFRP improves forecasting accuracy by 8.4% on average.

The approach enhances interpretability of predictions.

Extensive experiments validate the effectiveness across seven datasets.

Abstract

Deep learning models such as MLP, Transformer, and TCN have achieved remarkable success in univariate time series forecasting, typically relying on sliding window samples from historical data for training. However, while these models implicitly compress historical information into their parameters during training, they are unable to explicitly and dynamically access this global knowledge during inference, relying only on the local context within the lookback window. This results in an underutilization of rich patterns from the global history. To bridge this gap, we propose Predicting the Future by Retrieving the Past (PFRP), a novel approach that explicitly integrates global historical data to enhance forecasting accuracy. Specifically, we construct a Global Memory Bank (GMB) to effectively store and manage global historical patterns. A retrieval mechanism is then employed to extract similar patterns from the GMB, enabling the generation of global predictions. By adaptively combining these global predictions with the outputs of any local prediction model, PFRP produces more accurate and interpretable forecasts. Extensive experiments conducted on seven real-world datasets demonstrate that PFRP significantly enhances the average performance of advanced univariate forecasting models by 8.4\%. Codes can be found in https://github.com/ddz16/PFRP.