| July 24, 2012
In this study, we provide direct evidence supporting this anecdote and show that news analytics can be useful to capture the self-correcting process following periods of overreaction and underreaction.
Anecdotal evidence suggest that sectors experiencing hype tend to overreact leading to price reversion, while more lackluster sectors tend to rebound after a period of underperformance.
Bellow are some of our key results.
Conventional market wisdom postulates that a sector rotation strategy that allocates assets according to the stages of the business cycle should outperform the market. While there is evidence supporting the difference in the response of sectors to macroeconomic conditions (Hong, Torous and Valkanov (2007), and Eleswarapu and Tiwari (1996)), evidence remains mixed as to whether a sector rotation model actually outperforms a passive investment strategy. Using data since 1948, Stangl, Jacobsen, and Visaltanachoti (2009) find that a
sector rotation model
does not significantly outperform the market even if an investor perfectly anticipates the stages of the business cycle.
Other researchers, however, show that a sector rotation model conditional on information sets beyond the business cycle may be able to generate better returns than the market.
For example, Conover, Jensen, Johnson, and Mercer (2008) show that a strategy that overweighs cyclical stocks during periods of Fed easing and overweighs defensive stocks during periods of Fed tightening can generate outperformance. Jacobsen and Visaltanachoti (2009) also show that sector market timing based on summer and winter patterns in U.S. sectors outperforms a buy and hold portfolio.
In this study, we reexamine the sector rotation approach by measuring the sector return sensitivity to news and sentiment. Unlike
traditional sector rotation models
that help investors identify and participate in new trending sectors, we try to identify sectors that have likely overreacted to news sentiment or underreacted through different market environments. To measure the degree of overreaction or underreaction across sectors and time, we estimate the sector sensitivity as the absolute value of the coefficient in the time-series regression of sector ETF returns on changes in the RavenPack Market Sentiment Index - a news-based proxy of market sentiment.
The sector sensitivity is measured after controlling for sector sentiment and traditional risk factors. The higher the sensitivity measure, the more likely the sector will overreact to market sentiment and be more likely to revert in the future. The lower the sensitivity, the more likely the sector may underreact and rebound in the future. Following this logic, we hypothesize that the sector with higher sensitivity to market sentiment will yield lower return in the future compared to the sector with lower sensitivity.
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.