| December 01, 2011
To capture the overall sentiment of the market, we construct a news sentiment index based on the Event Sentiment Score (ESS) developed by RavenPack.
The index is constructed using a simple, intuitive, and robust approach capturing the sentiment momentum on the US market over a three month period.
This is the second edition of the new RavenPack Research Series. In this report, we take a closer look at the RavenPack Sentiment Index and its relationship to financial market returns.
Although historically quantitative investing is able to beat the market by using simple factors like size, momentum, or value to earn excess risk adjusted returns, the performance of traditional factors has shown significant decay after large amounts of assets have been drawn into the quantitative asset management business.
One way to discover alpha opportunities is to identify new data sources that are able to capture the mispricing in the market and that are not exploited too extensively.
One of the most recent developments in the pursuit of the new “Holy Grail” lies in the field of behavioral finance. Researchers are striving to come up with non-economic factors, such as investor sentiment, as a possible predictor of asset prices. Although we have already seen some encouraging results, they are far from satisfactory for at least two reasons: (1) Most of the commonly-used proxies for market sentiment are based on indirect measures inferred from financial markets using a top-down approach. Such measures include the discount on closed-end funds, the Put-Call Ratio, the optionimplied volatility, or IPO volume, just to name a few. The major drawback for this type of sentiment indicator is that it's not orthogonal to asset price, which is usually the variable that a sentiment index should try to explain. (2) Most sentiment indicators including survey based measures such as the University of Michigan Consumer Confidence Index or the Conference Board Consumer Confidence Index can only be updated at very low frequency such as monthly or quarterly and will be of little use to quantitative asset management where timeliness is crucial.
In this paper, we introduce a new measure of market sentiment - the
RavenPack Sentiment Index
. Unlike other sentiment proxies, the RavenPack Sentiment Index is comprehensive, direct, and up-to-date. It's constructed using a bottom-up approach and exhibits a high correlation with overall market movements. In the next section, we will briefly introduce the sentiment index construction methodology and examine the causality relationship between the RavenPack Sentiment Index and stock market performance. We will discuss the economic significance of the RavenPack Sentiment Index by studying the profitability of a sentiment-based trading strategy. Finally, we provide some interesting conclusions and recommendations for further research.
Please use your business email. If you don't have one, please email us at firstname.lastname@example.org.
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 email@example.com. 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.