Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Silin, Wang, Dong, Zheng, Haoqi, Jin, Ruochun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.16643
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910759083048960
author Yang, Silin
Wang, Dong
Zheng, Haoqi
Jin, Ruochun
author_facet Yang, Silin
Wang, Dong
Zheng, Haoqi
Jin, Ruochun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16643
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation
Yang, Silin
Wang, Dong
Zheng, Haoqi
Jin, Ruochun
Artificial Intelligence
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.
title TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2412.16643