Related links
  About RavenPack
  Competencies
   
   

Impact of News Sentiment on Abnormal Stock Returns

Published Date: May 12, 2009
Author: Peter Ager Hafez

Brief:

The study provides insights into how RavenPack News Scores can be used in profitable trading strategies.

Abstract:

The purpose of this paper is to investigate the impact of news sentiment on abnormal stock return, which allows us to focus on company specific news events as opposed to news driving the overall market. The analysis is conducted on a portfolio of stocks including the constituents of the Dow Jones Industrial Average and the Eurostoxx50 covering the years 2005 through 2008. Based on a set of sentiment classifiers used to process textual input of news stories, we construct a set of events characterized by unique combinations of sentiment classifications. Out of 63 potential events, we find at least 39 events that show interesting results in terms of creating trading signals. Of these events about 50% translate into short strategies. In total 173,100 potential long and short trading signals are generated over the four year period. On average, the most profitable trading signals generated around 0.7% per trade over the five hours following the event, with hit ratios around 60-65%. In addition, we find that 62% of the interesting events hold positive average Information Ratios in at least three of the four years covered in the study.
   
 

Please fill out the following form to get more information:
 

* Mandatory items - without your responses to mandatory items, we cannot process your request.
   
 

Mr/Ms:
 

First Name:*
 

Last Name:*
 

Job Title:
 

Company Name:*
 

E-mail Address:*
 

Telephone Number:*
 

Address:
 

City:*
 

State (if within the United States):
 

Province (if outside the United States):
 

Zip / Postal Code:
 

Country:*
   
   

Type the characters you see in this picture (case-sensitive).