Summary
The REACTION signals continued to perform well in 2022 with metrics that met and exceeded average historical performance, despite one of the most challenging environments in recent times for quantitative equity strategies in which the S&P dropped nearly 20% and markets became increasingly macro-driven. A portfolio that traded all 3 REACTION entry points (t0 open + 60 min, t0 close, t1 open) with constant capital of $50M per entry point ($150M total) returned 11.4% with a Sharpe ratio of 1.38 as compared to an average annual return of 11.1% and Sharpe ratio of 1.99 between 2016-21. If trading were restricted to only the 500 most liquid stocks, the portfolio would have returned 9.2% with a Sharpe ratio of 1.39 in 2022, as compared to an average annual return of 7.3% with a Sharpe ratio of 1.59 between 2016-21. Additionally, when we apply the market direction filter (which was discovered in our 2021 research), the portfolio performance shows improvement. All results are inclusive of conservative cost assumptions. Strong performance that is uncorrelated to the market and to other strategies during a challenging environment has continued to attract clients and prospects for Leapday’s products.
Read as PDF
2022 Year In Review
2022 marked the end of a 13-year bull market with the S&P dropping 19.4% and NASDAQ dropping 33.1%. The quantitative easing and cheap money that fueled a record-setting stock market run were ended by the highest inflation numbers in 40 years, a hawkish Fed that continues to raise interest rates, macroeconomic uncertainty, and geopolitical instability. Amidst this macro environment, Leapday’s stock-specific REACTION signals continued to perform well.
In 2022, Leapday continued to grow its base of clients and prospects for its flagship REACTION product. In early 2022, we also had a successful launch of our SENTIMENT product, a proprietary NLP model that makes predictions of short-term price direction following news, an improvement over traditional sentiment analysis that simply identifies mood or tone without linking it to market behavior. We continued to conduct research to help clients maximize the value of the REACTION signals. We published a paper demonstrating that the largest losing trades are often due to exogenous factors in the form of news that is released which contradicts the signal and savvy investors can improve performance by exiting trades early in these situations.
Leapday also continued to find use cases for our signals beyond our core base of systematic hedge funds and proprietary trading firms. Our research report for fundamental investors indicated how this investor group can use REACTION signals to delay taking profits in already established positions, delay entering new positions to achieve better entry prices, or confirm initiating trades immediately after events to lock in the best prices. Finally, we ended the year by creating an Earnings Sentiment Indicator by aggregating our stock-specific REACTION signals into a daily sentiment indicator for the market’s overall earnings activity. We found that this macro indicator is predictive of down moves in the aggregate market and can be used as an overlay to a long equity portfolio to provide downside protection and enhance returns.
Outlining This Report
The remainder of this report provides an analysis of 2022 performance for the Leapday REACTION model. This report will provide summary trade performance metrics as well as performance for portfolios constructed using the top one-third of 3d REACTION signals. We include the following details in this 2022 report:
Our whitepaper “Trading Events: Predicting Reactions After Earnings Announcements” was first published in January 2021 and introduced the REACTION signals. This paper provided summary metrics for the performance of the REACTION signals including average returns, hit rate, and avg. winner / avg. loser. To continue providing updates on these metrics, this report will provide summary metrics for 2022 performance as compared to 2016-21. Like the whitepaper, it will break down performance by liquidity groups. Additionally, we apply the market direction filter that was discovered in our research in 2021 and provide the associated summary metrics.
For portfolios using $50M per entry point, we examine performance in 2022 as compared to 2016-21 (both without and with the market direction filter.) We also conduct the same analysis but restrict trading to only the most liquid 500 stocks. The full list of assumptions for constructing the portfolios is provided in the appendix.
Trade-level Performance
Below we present summary metrics using the top one-third of 3d REACTION signals for all 3 REACTION entry points (t0 open + 60 min, t0 close, t1 open). Metrics exclude trading costs. The breakdowns include results without and with the market direction filter and are further broken down by liquidity groups.
The liquidity groups were first introduced in the original REACTION whitepaper and are determined by a stock’s historical average trade value (calculated using the trailing 20 day average traded value). The 3 liquidity groups are:
Low Liquidity: <$3M historical average trade value
Medium Liquidity: $3M-$25M historical average trade value
High Liquidity: >$25M historical average trade value
Aggregate results for the t0 open + 60 min signals in 2022 are similar to the historical averages. The low liquidity group outperforms historical averages but the medium and high liquidity groups underperform. The market direction filter continues to improve performance of the signals in 2022 and outperforms historical averages for the low and high liquidity groups.
In 2022, the t0 close signals performed in line with historical averages. Medium liquidity stocks underperformed historical averages but high liquidity stocks outperformed. The market direction filter continued to improve performance in 2022.
At the aggregate level, the t1 open signals performance in 2022 was in line with historical averages and just slightly underperformed. While medium liquidity stocks underperformed historical averages, high liquidity stocks strongly outperformed.
Performance Update For Portfolios Using $50M Per Entry Point
Below we present performance for portfolios constructed using the top one-third of 3d REACTION signals for the t0 open + 60 min, t0 close, and t1 open entry points. We also construct a combined portfolio using all three entry points.
We begin with a chart that displays portfolio performance of the combined portfolio inclusive of costs. We show performance for a portfolio that trades all companies as well as a portfolio that restricts trading to only the most liquid 500 stocks. We provide performance without and with the market direction filter.
Below we provide a comparison of returns and Sharpe ratios for 2022 vs. historical results from 2016-2021. We examine these results for a portfolio that trades all companies as well as one that trades only the most liquid 500 stocks. These breakdowns include results without and with the market direction filter as well as without and with trading costs.
Combined portfolio returns for 2022 are similar to historical averages with a slight outperformance. Sharpe ratios in 2022 were below historical averages likely due to the increased volatility in the market relative to the full historical period. The combined portfolio returns for the liquid 500 stocks outpaced historical averages. Additionally, like previous years, results showed improvement when applying the market direction filter.
Breaking down the combined portfolio returns by entry points shows us that the t0 open + 60 min portfolio had negative returns and underperformed the historical averages while t0 close and t1 open portfolios strongly outperformed reflecting the trade-level performance shown earlier in which high liquidity stocks underperformed in 2022 for the t0 open + 60 min signals and outperformed for the t0 close and t1 open signals. The results continue to highlight the importance of using multiple entry points when trading earnings reactions.
Finally, we examine correlation between the return streams of the various portfolios and SPY.
As the table above indicates, the REACTION portfolios remain uncorrelated to SPY in 2022. Given the low correlations for all the different combinations of entry points and stock universe it is clear that REACTION provides a unique return stream that is not related to equity returns.
Conclusion
2022 was a challenging year for equity markets and quantitative equity strategies. The REACTION model, however, continued to produce strong out of sample performance. A combined portfolio using all 3 REACTION entry points exceeded its historical performance with the t0 close and t1 open entry points significantly exceeding the historical average. In addition, correlation between the returns of the REACTION portfolios and SPY show that the signals continue to provide an uncorrelated return stream. Double digit uncorrelated returns during a period in which the stock market dropped nearly 20% has continued to attract new clients and prospects in 2022 for the REACTION product.
Appendix - Assumptions Used In Portfolio Construction
We use the strongest one-third of the 3d REACTION signals for each entry point (t0 open + 60 min, t0 close, t1 open) to build a simulated portfolio. Below we present all the assumptions used in the portfolio construction.
Enter and exit trades as follows:
t0 open + 60min signal: Enter a trade 60 minutes after the open on the first day the market is open subsequent to a company’s earnings announcement (t0 open + 60 min) and exit the trade on the close 3 days later (t2 close).
t0 close signal: Enter a trade at the market close on the first day the market is open subsequent to a company’s earnings announcement (t0 close) and exit the trade on the close 3 days later (t3 close).
t1 open signal: Enter a trade at the market open on the second day the market is open subsequent to a company’s earnings announcement (t1 open) and exit the trade on the close 3 days later (t3 close).
Create a market-neutral portfolio by hedging trades using an opposite side trade in SPY with a beta-adjusted notional value that offsets the beta risk of the event trade.
Starting capital of $50M per entry point and $150M for the combined portfolio, assuming constant capital throughout the portfolio (i.e. - we do not reinvest profits).
Portfolio leverage used during periods of high activity
Trade no more than 6 percent of the starting capital per position.
Trade no more than 1.5 percent of a company’s historical average trade value per position for the t0 open + 60 min signal. Trade no more than 2 percent of a company’s historical average trade value per position for t0 close and t1 open signal. (The historical average trade value is calculated using the trailing 20 day average traded value.)
Beyond the two constraints on trade size stated above, trade equal weight.
Round-trip trading costs are based on breakpoints for liquidity group as follows:
Low (<$3M historical average trade value): 20 bps (40 bps for t0 open + 60 min signals)
Mid ($3M-$25M historical average trade value): 10 bps (20 bps for t0 open + 60 min signals)
High (>$25M historical average trade value): 5 bps (10 bps for t0 open + 60 min signals)
Costs are allocated half on entry and half on exit
In the metrics presented below, we assume $0 in hedge costs (for the SPY hedge) and the hedge does not use any equity or margin
Disclaimer
This paper is solely for informational purposes and is not an offer or solicitation for the purchase or sale of any security, nor is it to be construed as legal or tax advice. References to securities and strategies are for illustrative purposes only and do not constitute buy or sell recommendations. The information in this report should not be used as the basis for any investment decisions.
We make no representation or warranty as to the accuracy or completeness of the information contained in this report, including third-party data sources. The views expressed are as of the publication date and subject to change at any time.
Hypothetical performance has many significant limitations and no representation is being made that such performance is achievable in the future. Past performance is no guarantee of future performance.