By using a novel measure of investor attention, generated from InvestingChannel’s clickstream data on online financial news consumption, we can identify broad groups of stocks which are less efficiently priced and therefore where anomalies such as Value and Momentum are likely to produce greater cross sectional differentiation in returns. We also apply these groupings to proprietary ExtractAlpha stock selection signals.
Since it is likely that both the Relative Sentiment and Trend Following strategies will underperform at some points in the future, “a 50-50 combination of TF and RS might reduce the emotional volatility an investor may experience from holding only the underperforming strategy.”
Relative sentiment is an indicator that measures the positions, flows, and attitudes of institutional investors compared to those of individual investors–where institutions typically consist of large asset managers, insurance companies, pension funds, and endowments. In some instances, however–depending on the dataset and the asset class under consideration–institutions might also include hedge funds, CTAs, and other large speculators.
We examine Sentix sentiment indices for use in tactical asset allocation. In particular, we construct monthly relative sentiment factors for the U.S., Europe, Japan, and Asia ex-Japan by taking the difference in 6-month economic expectations between each region's institutional and individual investors. These factors (along with one-month forward equity returns) then serve as inputs to a wide array of machine learning algorithms. Employing combinatorial cross-validation and adjusting for data snooping, we find relative sentiment factors have robust and significant predictive power in all four regions; that they surpass both standalone sentiment and time-series momentum in terms of informational content; and that they demonstrate the ability to identify the subsequent best- and worst-performing global equity markets from along a cross-section. The results are consistent with previous findings on relative sentiment, discovered using unrelated datasets.
The application of machine learning models to Sentix relative sentiment data appears to extract more predictive information than our original, simplistic approach was capable of.
An interesting question is do the trades of the more sophisticated institutional investors against anomalies provide information on returns? To answer that question, Yangru Wu and Weike Xu, authors of the study “Changes in Ownership Breadth and Capital Market Anomalies,” published in the February 2022 issue of The Journal of Portfolio Management, examined whether the entries and exits of informed institutional investors (or ownership breadth changes) interact with the aforementioned 11 anomaly signals studied by Stambaugh and Yuan can be used to improve the performance of anomaly-based strategies. They explained that they emphasized institutions’ new entries and exits because they could be triggered by private information and correlated with future earnings news, thereby capturing useful information regarding future stock returns. To determine if the trades of the institutional investors were informed, they sorted all stocks into 10 decile portfolios based on quarterly changes in ownership breadth. Their data sample covered all NYSE/AMEX/Nasdaq common stocks from May 1981 to May 2018.
The weight of the evidence suggests we recently exited a secular bull market driven by high real earnings growth and have entered a secular bear market driven by high inflation. The takeaway is that while investors have become highly conditioned to buy the dip, the current dip is occurring with relative sentiment significantly bearish (i.e., retail likes equities more than institutions). Historically, that has not been a great time to buy equities.
Can market sentiment be derived from the tunes that your fellow countrymen are listening to? According to the research summarized here you'll find that there is important market information buried in the listening habits of Spotify users.