"We found multiple benefits to using the Estimize dataset; especially in
the case of short term applications in which accuracy is essential."
—Deutsche Bank Quant Research
Want to learn more about how you can leverage our exclusive earnings data set? Contact us using this form to learn about accessing our raw data or Factor Model →
In the pre earnings period, the Estimize Consensus is a far superior representation of true market expectations due to the size, diversity and frequency of engagement of Estimize contributors. This means you can arbitrage the delta between the Estimize and Wall Street Consensus in the two week period leading into each earnings report.
The more representative Estimize Consensus can greatly improve the classic post earnings drift strategy used by systematic quants over the past 25 years. We found 65bps of residual return in the five days post earnings when there are large beats and misses of the Estimize Consensus. You can also identify potential misses, which produce negative price reaction historically and create volatility in certain stat arb strategies.
Due to a more honest dispersion of expectations within the Estimize data set relative to Wall Street, you can identify mispricing in vol prior to an earnings report. Larger dispersion of estimates for a given stock relative to that stock's previous reports results in more realized vol in the post earnings period than the implied vol.
The Wolf Research team found that an Earnings Yield strategy replacing Thomson Reuters I/B/E/S estimates with Estimize generated 1,000 basis points of alpha per year compared to the Russell 3,000 index.
In their paper, the Wolf Research team constructs several risk mitigation and enhanced value strategies, stating, "For long-term value investors, we show how Estimize data can be used to boost performance. We also overlay our enhanced value strategy with a low risk tilt (by avoiding earnings uncertainty) to further improve return and reduce risk."
From "More Accurate and Timely Estimates Lead to Better Investment Strategies"
McKinley Capital Research the negative deviation stocks underperformed the S&P 500 by 168 basis points (“bps”) on an unweighted basis and -11 bps on a weighted basis.
The combined results of the pre-announcement and post-announcement effects, suggest several ways that advisers might use “crowd-sourced” earnings estimates. Avoid owning stocks when the “crowdsourced” earnings estimate is first observed to be significantly below street estimates. Hold, or consider buying stocks with significant positive earnings surprise — especially when the actual earnings number exceeds the “crowd-sourced” estimate. Sell earnings misses with extreme caution! Contrarians might even consider buying on initial down moves in stocks with earnings misses!
From "Improving Earnings Forecasts with Estimize Crowd Sourced Data"
The Deutsche Bank Quantitative Research team "On A Post Earnings Announcement Drift Strategy"
Deutsche Bank Quant Research found multiple benefits to using the Estimize dataset; especially in short term applications where accuracy is essential. The diversity of contributors provides a greater spectrum of information which improves investment strategies.
University of San Diego, Biljana Abebambo & Barbara Bliss "On More Accurate Estimates And True Market Expectations"
University of San Diego researchers found that the Estimize consensus produces errors that are more strongly associated with abnormal returns, suggesting that it is a superior measure of the market’s true expectation.
Leigh Drogen & Vinesh Jha, Former Head of Starmine Quant Research "Generating Abnormal Returns Using Crowdsourced Earnings Forecasts from Estimize"
In this white paper, the internal Estimize quantitative research team outlines the data available as well as several alpha producing systematic strategies which are easily tested and put into production.
Rice University, Rick Johnston "The Value of Crowdsourced Earnings Forecasts"
Estimize is a market solution to the inherent bias of sell-side analyst forecasts, which produces more reliable and timely estimates due to its size and diversity. We find evidence that the incremental usefulness of Estimize in forecasting earnings and proxying for the market’s expectation increases with the number of contributors. This illustrates that the value of crowdsourcing is a function of crowd size.
Michigan State University, Zhi Da and Xing Huang “Harnessing the Wisdom of Crowds”
The findings suggest that the Estimize give-to-get model prevents herding behavior and encourages participants to share their independent expectations thereby delivering a more accurate consensus.
University of Kentucky, Russell Jame "Does Crowdsourced Research Discipline Research Analysts"
The findings suggest that the more accurate and less biased Estimize Consensus has had a reflexive effect on the accuracy of sell side analyst estimates in recent years. Competition from Estimize seems to be driving this behavior.
Estimize as a crowdsourcing platform represents a market solution to the shortcomings associated with sell-side analyst forecasts perhaps resulting from their incentives. The application of technology to enhance the information environment of firms is innovative and possibly revolutionary.
Rick Johnston, Rice University, “Competition for Sell-Side Analysts?”
Our estimates are quoted by leading media publications and tv networks…
Request more info now »
or call us at 212-634-9085