On Friday, 2017-05-26, at 10:00 in the Orange Room of Jožef Stefan Institute, Nastya Fedyk from Harvard Business School will speak about estimating the effect of attention to news on financial markets, using quasi-random variation in positioning of news articles on the Bloomberg terminal. He will focus on a category of news articles, some of which are pinned to the prominent “front page” positions at the top of the news screen in a process independent of their content. This offers a natural experiment in positioning between the articles that are pinned and those that are not. The front page and non-front page articles are indistinguishable by either algorithmic analysis, or by the target audience of active finance professionals. He finds that pinning a news article to the front page leads to 280% higher trading volumes and 180% larger price changes within the first ten minutes after publication. These articles also see a much stronger short-term price drift, with 21% higher continuation in returns at the five-minute level. The effect is strongest during the first 30-45 minutes after the news, and partially reverses over subsequent hours. A comparison against differential reactions following news articles of varying editorial importance indicates that news positioning plays an even stronger role in driving market activity than news importance.
- Seminar: Anaphora and coreference resolution: still a hard nut to crack?
- Seminar: SHL Dataset – A multimodal transportation dataset collected with smartphones
- Lecture: Design Optimization and Design Exploration in Space Engineering
- SLAIS general assembly
- Slovenian Conference on Artificial Intelligence and Informatica anniversary issue on artificial intelligence