TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation

TL;DR

TimeRAG enhances large language model-based time series forecasting by retrieving similar historical sequences using Dynamic Time Warping and incorporating them into prompts, leading to improved prediction accuracy across diverse datasets.

Contribution

The paper introduces TimeRAG, a novel retrieval-augmented framework that leverages a knowledge base of historical sequences to boost LLM forecasting performance.

Findings

Average prediction accuracy improved by 2.97%.

Effective retrieval of similar sequences enhances forecasting.

Applicable across multiple domain datasets.

Abstract

Although the rise of large language models (LLMs) has introduced new opportunities for time series forecasting, existing LLM-based solutions require excessive training and exhibit limited transferability. In view of these challenges, we propose TimeRAG, a framework that incorporates Retrieval-Augmented Generation (RAG) into time series forecasting LLMs, which constructs a time series knowledge base from historical sequences, retrieves reference sequences from the knowledge base that exhibit similar patterns to the query sequence measured by Dynamic Time Warping (DTW), and combines these reference sequences and the prediction query as a textual prompt to the time series forecasting LLM. Experiments on datasets from various domains show that the integration of RAG improved the prediction accuracy of the original model by 2.97% on average.