Search
× Search
Wednesday, February 5, 2025

Archived Discussions

Recent member discussions

The Algorithmic Traders' Association prides itself on providing a forum for the publication and dissemination of its members' white papers, research, reflections, works in progress, and other contributions. Please Note that archive searches and some of our members' publications are reserved for members only, so please log in or sign up to gain the most from our members' contributions.

Accern used 600,000 Earnings Articles in an Event-Driven Backtest

photo

 Kumesh Aroomoogan, Co-Founder and CEO at Accern

 Thursday, April 23, 2015

We recently backtested over 600,000 news and blog articles related to company earnings (2.5 years length) with the help of Quantopian community members. The results were very interesting and I am excited to share them with you. The purpose of the backtest was to identify the performance of trading on pre/post earning information in real-time using sentiment indicators and to also identify which segment of earnings information generated the most returns. Accern found that Financial Ratings (a segment of Company Earnings) is one of the best predictor for stock price movements with a total return of 322% in 2.5 years of backtesting 600,000 earnings articles. Full Backtest Report: https://www.quantopian.com/posts/accern-event-driven-earnings-focused-news-and-blog-backtest-results-pdf-report-attached


Print

3 comments on article "Accern used 600,000 Earnings Articles in an Event-Driven Backtest"

photo

 Rajiv Malhotra, Systems Trader at Trex Stock Trading

 Saturday, April 25, 2015



What is the holding period of a position. or do you use some profit target? Returns look abnormally high


photo

 Kumesh Aroomoogan, Co-Founder and CEO at Accern

 Saturday, April 25, 2015



The holding period ranges in days. There is no fixed holding period. It long / short / exit when our specified conditions are matched in the data. For example if we have a long position on Apple, it will only exit that position when we get a sell / short signal (ex. negative rumor / news about to happen). A profit target would be an interesting thing to try next!


photo

 Larry Kase, Financial Analyst, Publisher QAInvestor.com

 Thursday, April 30, 2015



Prior to discussing the underlying hypothesis the is an overriding consideration; what process was applied to assume that assumed orders could be executed. Order execution is the consistently ignored component of virtually all back testing exercises. The failure impeaches the process and renders the results misleading and distorted. Also, how does one know that any piece of information is bad or good. Most financial reports are quite complex. Rumors are fleeting wisps of conjecture and speculation. Is clairvoyance required?

Please login or register to post comments.

TRADING FUTURES AND OPTIONS INVOLVES SUBSTANTIAL RISK OF LOSS AND IS NOT SUITABLE FOR ALL INVESTORS
Terms Of UsePrivacy StatementCopyright 2018 Algorithmic Traders Association