FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis

TL;DR

FinMultiTime is a comprehensive, large-scale multimodal dataset for financial time-series analysis, integrating diverse data sources across markets to improve prediction accuracy and facilitate advanced research.

Contribution

This paper introduces FinMultiTime, the first large-scale, multimodal financial dataset aligning four different modalities across multiple markets and time resolutions.

Findings

Scale and data quality significantly improve prediction accuracy.

Multimodal fusion provides moderate gains in Transformer models.

A reproducible pipeline allows seamless dataset updates.

Abstract

Pure time series forecasting tasks typically focus exclusively on numerical features; however, real-world financial decision-making demands the comparison and analysis of heterogeneous sources of information. Recent advances in deep learning and large scale language models (LLMs) have made significant strides in capturing sentiment and other qualitative signals, thereby enhancing the accuracy of financial time series predictions. Despite these advances, most existing datasets consist solely of price series and news text, are confined to a single market, and remain limited in scale. In this paper, we introduce FinMultiTime, the first large scale, multimodal financial time series dataset. FinMultiTime temporally aligns four distinct modalities financial news, structured financial tables, K-line technical charts, and stock price time series across both the S&P 500 and HS 300 universes. Covering 5,105 stocks from 2009 to 2025 in the United States and China, the dataset totals 112.6 GB and provides minute-level, daily, and quarterly resolutions, thus capturing short, medium, and long term market signals with high fidelity. Our experiments demonstrate that (1) scale and data quality markedly boost prediction accuracy; (2) multimodal fusion yields moderate gains in Transformer models; and (3) a fully reproducible pipeline enables seamless dataset updates.