MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
This addresses the problem of adapting LLMs for multivariate time series forecasting in domains like finance or healthcare, though it is incremental as it builds on existing LLM capabilities.
The paper tackles multivariate time series forecasting by introducing MultiCast, a zero-shot LLM-based approach that enables LLMs to handle multivariate inputs through token multiplexing and quantization, achieving competitive RMSE results and reduced execution time on three real-world datasets.
Predicting future values in multivariate time series is vital across various domains. This work explores the use of large language models (LLMs) for this task. However, LLMs typically handle one-dimensional data. We introduce MultiCast, a zero-shot LLM-based approach for multivariate time series forecasting. It allows LLMs to receive multivariate time series as input, through three novel token multiplexing solutions that effectively reduce dimensionality while preserving key repetitive patterns. Additionally, a quantization scheme helps LLMs to better learn these patterns, while significantly reducing token use for practical applications. We showcase the performance of our approach in terms of RMSE and execution time against state-of-the-art approaches on three real-world datasets.