News Sensitivity in Sector Rotation Models

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.

News Sensitivity Varies Across Sectors:

• Industrials has the highest overall correlation between news sentiment and sector returns, while Consumer Goods has the lowest correlation.

• Financials, Telecoms, and Consumer Goods are typically more highly correlated to market than to sector sentiment.

News Sensitivity Changes in Bullish and Bearish Markets

• The Oil & Gas sector has a low correlation with sector sentiment in bullish markets but a high correlation in bearish markets. The opposite pattern is observed in Financials.

• Technology is more affected by sector sentiment during bullish markets, but more affected by market sentiment during bearish markets. Similar results are found for Utilities, while Oil & Gas and Consumer Services show the opposite relationship.

News Sensitivity Adds Value to Sector Rotation Models

• Following a period of over- or under-reaction to news sentiment, it takes about 2 to 6 months for market prices to correct themselves.

• With a 6-month holding period, our sector rotation strategy generates an annualized return of 9.54% with an Information Ratio of 1.10 and a Hit Ratio of 0.68.

Introduction

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.