Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Madarasingha, Chamara, Sohrabi, Nasrin, Tari, Zahir
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913872123789312
author Madarasingha, Chamara
Sohrabi, Nasrin
Tari, Zahir
author_facet Madarasingha, Chamara
Sohrabi, Nasrin
Tari, Zahir
contents Time-series prediction or forecasting is critical across many real-world dynamic systems, and recent studies have proposed using Large Language Models (LLMs) for this task due to their strong generalization capabilities and ability to perform well without extensive pre-training. However, their effectiveness in handling complex, noisy, and multivariate time-series data remains underexplored. To address this, we propose LLMPred which enhances LLM-based time-series prediction by converting time-series sequences into text and feeding them to LLMs for zero shot prediction along with two main data pre-processing techniques. First, we apply time-series sequence decomposition to facilitate accurate prediction on complex and noisy univariate sequences. Second, we extend this univariate prediction capability to multivariate data using a lightweight prompt-processing strategy. Extensive experiments with smaller LLMs such as Llama 2 7B, Llama 3.2 3B, GPT-4o-mini, and DeepSeek 7B demonstrate that LLMPred achieves competitive or superior performance compared to state-of-the-art baselines. Additionally, a thorough ablation study highlights the importance of the key components proposed in LLMPred.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02389
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting
Madarasingha, Chamara
Sohrabi, Nasrin
Tari, Zahir
Machine Learning
Artificial Intelligence
Time-series prediction or forecasting is critical across many real-world dynamic systems, and recent studies have proposed using Large Language Models (LLMs) for this task due to their strong generalization capabilities and ability to perform well without extensive pre-training. However, their effectiveness in handling complex, noisy, and multivariate time-series data remains underexplored. To address this, we propose LLMPred which enhances LLM-based time-series prediction by converting time-series sequences into text and feeding them to LLMs for zero shot prediction along with two main data pre-processing techniques. First, we apply time-series sequence decomposition to facilitate accurate prediction on complex and noisy univariate sequences. Second, we extend this univariate prediction capability to multivariate data using a lightweight prompt-processing strategy. Extensive experiments with smaller LLMs such as Llama 2 7B, Llama 3.2 3B, GPT-4o-mini, and DeepSeek 7B demonstrate that LLMPred achieves competitive or superior performance compared to state-of-the-art baselines. Additionally, a thorough ablation study highlights the importance of the key components proposed in LLMPred.
title Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.02389