MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913359884976128 |
|---|---|
| author | Chatzigeorgakidis, Georgios Lentzos, Konstantinos Skoutas, Dimitrios |
| author_facet | Chatzigeorgakidis, Georgios Lentzos, Konstantinos Skoutas, Dimitrios |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs Chatzigeorgakidis, Georgios Lentzos, Konstantinos Skoutas, Dimitrios Machine Learning Artificial Intelligence 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. |
| title | MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.14748 |