A Language Model-Guided Framework for Mining Time Series with Distributional Shifts

TL;DR

This paper introduces a framework that leverages large language models and data interfaces to collect and augment time series datasets, especially under distributional shifts, enhancing model robustness and performance.

Contribution

It proposes a novel approach using language models to gather and generate supplementary time series data that share key properties with original datasets, addressing data scarcity and privacy issues.

Findings

Collected datasets share critical statistical properties with primary data

Fine-tuned forecasting models perform comparably to non-fine-tuned models

Method effectively enhances data quantity and diversity under distributional shifts

Abstract

Effective utilization of time series data is often constrained by the scarcity of data quantity that reflects complex dynamics, especially under the condition of distributional shifts. Existing datasets may not encompass the full range of statistical properties required for robust and comprehensive analysis. And privacy concerns can further limit their accessibility in domains such as finance and healthcare. This paper presents an approach that utilizes large language models and data source interfaces to explore and collect time series datasets. While obtained from external sources, the collected data share critical statistical properties with primary time series datasets, making it possible to model and adapt to various scenarios. This method enlarges the data quantity when the original data is limited or lacks essential properties. It suggests that collected datasets can effectively supplement existing datasets, especially involving changes in data distribution. We demonstrate the effectiveness of the collected datasets through practical examples and show how time series forecasting foundation models fine-tuned on these datasets achieve comparable performance to those models without fine-tuning.