Event-Driven Trading and the “New News”

Abstract

Two information revolutions are underway in trading and investing. Most headlines focus on structured quantitative market information at ever higher frequencies, but the other technology revolution in trading and investing is driven by qualitative, textual, and relationship information. The IBM computer Watson’s overwhelming Jeopardy victory demonstrated how good machines can get at this. News analysis is a focus of language technology in finance. In this article, Leinweber and Sisk include event studies and show U.S. portfolio simulation results for “pure news” signals applied over the period 2006–2009 as well as a true out-of-sample period in 2010, which indicates alpha in excess of 10% a year. The authors also describe other applications of automated qualitative analysis for information-driven social media client relations.

TOPICS: Equity portfolio management, big data/machine learning, security analysis and valuation