Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Yunkai, Zhang, Yawen, Zheng, Ming, Chen, Kezhen, Gao, Chongyang, Ge, Ruian, Teng, Siyuan, Jelloul, Amine, Rao, Jinmeng, Guo, Xiaoyuan, Fang, Chiang-Wei, Zheng, Zeyu, Yang, Jie
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917141388722176
author Zhang, Yunkai
Zhang, Yawen
Zheng, Ming
Chen, Kezhen
Gao, Chongyang
Ge, Ruian
Teng, Siyuan
Jelloul, Amine
Rao, Jinmeng
Guo, Xiaoyuan
Fang, Chiang-Wei
Zheng, Zeyu
Yang, Jie
author_facet Zhang, Yunkai
Zhang, Yawen
Zheng, Ming
Chen, Kezhen
Gao, Chongyang
Ge, Ruian
Teng, Siyuan
Jelloul, Amine
Rao, Jinmeng
Guo, Xiaoyuan
Fang, Chiang-Wei
Zheng, Zeyu
Yang, Jie
contents Time-series data is critical across many scientific and industrial domains, including environmental analysis, agriculture, transportation, and finance. However, mining insights from this data typically requires deep domain expertise, a process that is both time-consuming and labor-intensive. In this paper, we propose \textbf{Insight Miner}, a large-scale multimodal model (LMM) designed to generate high-quality, comprehensive time-series descriptions enriched with domain-specific knowledge. To facilitate this, we introduce \textbf{TS-Insights}\footnote{Available at \href{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}.}, the first general-domain dataset for time series and language alignment. TS-Insights contains 100k time-series windows sampled from 20 forecasting datasets. We construct this dataset using a novel \textbf{agentic workflow}, where we use statistical tools to extract features from raw time series before synthesizing them into coherent trend descriptions with GPT-4. Following instruction tuning on TS-Insights, Insight Miner outperforms state-of-the-art multimodal models, such as LLaVA \citep{liu2023llava} and GPT-4, in generating time-series descriptions and insights. Our findings suggest a promising direction for leveraging LMMs in time series analysis, and serve as a foundational step toward enabling LLMs to interpret time series as a native input modality.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11251
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language
Zhang, Yunkai
Zhang, Yawen
Zheng, Ming
Chen, Kezhen
Gao, Chongyang
Ge, Ruian
Teng, Siyuan
Jelloul, Amine
Rao, Jinmeng
Guo, Xiaoyuan
Fang, Chiang-Wei
Zheng, Zeyu
Yang, Jie
Machine Learning
Time-series data is critical across many scientific and industrial domains, including environmental analysis, agriculture, transportation, and finance. However, mining insights from this data typically requires deep domain expertise, a process that is both time-consuming and labor-intensive. In this paper, we propose \textbf{Insight Miner}, a large-scale multimodal model (LMM) designed to generate high-quality, comprehensive time-series descriptions enriched with domain-specific knowledge. To facilitate this, we introduce \textbf{TS-Insights}\footnote{Available at \href{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}{https://huggingface.co/datasets/zhykoties/time-series-language-alignment}.}, the first general-domain dataset for time series and language alignment. TS-Insights contains 100k time-series windows sampled from 20 forecasting datasets. We construct this dataset using a novel \textbf{agentic workflow}, where we use statistical tools to extract features from raw time series before synthesizing them into coherent trend descriptions with GPT-4. Following instruction tuning on TS-Insights, Insight Miner outperforms state-of-the-art multimodal models, such as LLaVA \citep{liu2023llava} and GPT-4, in generating time-series descriptions and insights. Our findings suggest a promising direction for leveraging LMMs in time series analysis, and serve as a foundational step toward enabling LLMs to interpret time series as a native input modality.
title Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language
topic Machine Learning
url https://arxiv.org/abs/2512.11251