Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.02702v1</id>\n    <title>FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing</title>\n    <updated>2026-03-03T07:45:57Z</updated>\n    <link href='https://arxiv.org/abs/2603.02702v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.02702v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The financial domain involves a variety of important time-series problems. Recently, time-series analysis methods that jointly leverage textual and numerical information have gained increasing attention. Accordingly, numerous efforts have been made to construct text-paired time-series datasets in the financial domain. However, financial markets are characterized by complex interdependencies, in which a company's stock price is influenced not only by company-specific events but also by events in other companies and broader macroeconomic factors. Existing approaches that pair text with financial time-series data based on simple keyword matching often fail to capture such complex relationships. To address this limitation, we propose a semantic-based and multi-level pairing framework. Specifically, we extract company-specific context for the target company from SEC filings and apply an embedding-based matching mechanism to retrieve semantically relevant news articles based on this context. Furthermore, we classify news articles into four levels (macro-level, sector-level, related company-level, and target-company level) using large language models (LLMs), enabling multi-level pairing of news articles with the target company. Applying this framework to publicly-available news datasets, we construct \\textbf{FinTexTS}, a new large-scale text-paired stock price dataset. Experimental results on \\textbf{FinTexTS} demonstrate the effectiveness of our semantic-based and multi-level pairing strategy in stock price forecasting. In addition to publicly-available news underlying \\textbf{FinTexTS}, we show that applying our method to proprietary yet carefully curated news sources leads to higher-quality paired data and improved stock price forecasting performance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-03T07:45:57Z</published>\n    <arxiv:comment>14 pages</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Jaehoon Lee</name>\n    </author>\n    <author>\n      <name>Suhwan Park</name>\n    </author>\n    <author>\n      <name>Tae Yoon Lim</name>\n    </author>\n    <author>\n      <name>Seunghan Lee</name>\n    </author>\n    <author>\n      <name>Jun Seo</name>\n    </author>\n    <author>\n      <name>Dongwan Kang</name>\n    </author>\n    <author>\n      <name>Hwanil Choi</name>\n    </author>\n    <author>\n      <name>Minjae Kim</name>\n    </author>\n    <author>\n      <name>Sungdong Yoo</name>\n    </author>\n    <author>\n      <name>SoonYoung Lee</name>\n    </author>\n    <author>\n      <name>Yongjae Lee</name>\n    </author>\n    <author>\n      <name>Wonbin Ahn</name>\n    </author>\n  </entry>"
}