| September 27, 2012
Measuring the sentiment on companies from news provides value beyond traditional quantitative factors in a stock selection process.
In this report, we construct a company sentiment indicator from news, and look at how prices are impacted over several investment horizons. Below are some of our key results:
Performance Differs Across Size When Trading on Sentiment
Stock Prices Overreact to Extreme Positive Sentiment
Stocks with Negative Sentiment Underperform Positive Sentiment Stocks
With the continuous innovations made in news analytics, it has become more easily attainable for investors to make their models news aware – both when it comes to scheduled and unscheduled news. Incorporating news into an investment framework is desirable, since in theory, news affects risk and return expectations - and consequently the pricing of securities. Although, the concept of applied news analytics has been around for more than a decade, we are still in an early stage in understanding different trading and investment applications. As part of our continued research efforts, it’s our objective to help shed some light on this topic.
Recently, we considered how changes in company sentiment could be useful for shortterm stock selection - especially, when focusing on intraday and up to 2 days after a significant change in a company’s sentiment. In this paper, we build on this idea, and extend our analysis to the medium-term considering investment horizons of 1 week to 1 month. The methodology disclosed here is similar to one shared in a previous study, except we now look at sentiment levels rather than sentiment changes. In addition, we try to: a) capture directional sentiment strength, and b) adjust for size and sector news flow differences.
Our research is based on the RavenPack News Analytics 3.0 dataset, a real–time news analytics service that covers more than 30,000 publicly traded companies worldwide. The archive extends back to 2000 with more than 12 years of millisecond timestamped historical data.
In the next section, we will briefly describe the construction of a RavenPack Company Sentiment Indicator and look at some of its basic characteristics. Later we present the future return pattern following positive and negative sentiment values and consider the effect of size on signal performance. We also illustrate the economic significance of a trading strategy based on the sentiment indicator and reveal our conclusions.
Please use your business email. If you don't have one, please email us at email@example.com.
We will process your personal data with the purpose of managing your personal account on
RavenPack and offering our services. You can exercise your rights of access, rectification,
erasure, restriction of processing, data portability and objection by emailing us at firstname.lastname@example.org. For more information, you can
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.