LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · LLM新闻事件漂移研究Matériel2 min de lectureRédaction DisconfirmAI

New Study Finds US Markets Underreact to Hard Data, Overreact to Soft Stories via AI Classification

Research shows LLM-tagged quantitative news drifts for weeks while story-driven news reverses quickly, offering a benchmark for AI-assisted investing.

2026-10-20 12:00 GMT+8

A recent study accepted at the ICAIF 2026 workshop, titled "Buy the Rumor, Sell the News: When Is News Priced In?", analyzed 4.57 million financial news articles covering approximately 3,000 US stocks from 2023 to 2026 using a large language model (LLM). The researchers distilled an LLM teacher into a compact classifier via active learning, assigning each article one of 17 event tags and five attributes, while clustering articles to separate first reports from follow-up coverage.

By measuring beta-adjusted abnormal returns around 1.68 million stock-day events, the study identified three key results. First, price moves associated with news concentrate before and at publication: the cumulative move in the news direction by the close of publication day is 2.8 times its value twenty days later. For rumor-flagged events, directional returns are concentrated around the rumor itself, with little incremental return at subsequent linked non-rumor events.

Second, compared to neutral-sentiment controls, markets underreact to numbers and overreact to stories. Quantified fundamental news (earnings, dividends, guidance, analyst actions) continues to drift in the direction of the news for weeks, whereas soft story-driven news (launches, macro commentary, leadership changes) gives back its move. Third, news carries width as well as direction: neutral news raises publication-day volatility.

The study produces a table of measured drift for each event tag, usable as a prior in news-conditioned forecasting models. This suggests that for readers using AI in investment research, distinguishing between the "quantitative" and "narrative" nature of news is critical for assessing market absorption speed and potential trading signals.

Connexion / Inscription
LectureRechercheRadarCadre d'investissement

Sources

  • arxiv.org↗
Sujet

LLM新闻事件漂移研究

一项针对美国股市的大规模研究利用大语言模型(LLM)重新定义了市场对新闻的反应机制。该研究分析了2023年至2026年间覆盖约3,000只美股的457万篇金融新闻文章,通过LLM将新闻标记为17种事件类型,并测量了168万个股票日事件的异常…

3 étapes0 piècesMis à jour 2026-10-26 17:03

Comment on en est arrivé là

  1. 2026-08-14论文《Buy the Rumor, Sell the News: When Is News Priced In?》初版提交至arXiv,提出利用LLM分类器分析金融新闻事件与市场反应的关系。arxiv.org ↗
  2. 2026-10-18论文修订版(v2)发布并被ICAIF 2026会议接收,详细披露了457万篇文章的分析结果,确认市场对硬数据反应不足、对软故事过度反应的结论。arxiv.org ↗
  3. 2026-10-20媒体广泛报道该研究,指出LLM标记的量化新闻存在数周价格漂移,而故事型新闻迅速回吐,为AI投研提供事件反应基准。arxiv.org ↗

Ce qui reste non résolu

  • LLM分类器的误标率是否会影响特定小盘股或低流动性资产的事件漂移测量?
  • 随着LLM模型的迭代更新,这种基于旧训练数据的新闻分类偏差是否会改变市场对新闻的反应模式?
  • 该研究发现的‘硬数据反应不足’现象在不同市场周期(如高波动期与低波动期)中是否具有稳定性?
Lire le sujet complet →
Continuer la recherche →