Market-neutral portfolio construction with an event-based signal PART 2
In this report we build a market-neutral portfolio using Leapday’s REACTION signals which are generated 60 minutes after the open on the first day of trading subsequent to a company's earnings announcement. In a previous report, we built a portfolio using REACTION signals generated just before the close on the first day of trading subsequent to a company’s earnings announcement. We find that these two portfolios have a low correlation of returns and when combined into a single portfolio have superior performance. The combined portfolio has an annualized return of 9.9% between 2016-2020, a Sharpe ratio of 2.14, a maximum drawdown of -3.5%, and a correlation to SPY of 0.06. All of the portfolio results are inclusive of conservative trading cost assumptions. These results are robust to stock liquidity.
Read as PDF
In a previous report, we constructed an event-driven portfolio using REACTION signals generated after earnings announcements. We focused that report on signals released just before the close on the first day the market is open after a company’s earnings announcement. In this report, we will examine the signal that is released 60 minutes after the open on the first day the market is open after an announcement. The motivation behind this research is twofold. First, like our previous report, we seek to show the performance of the signals in a realistic portfolio setting. Second, we seek to study the relationship between the signals generated 60 minutes after the open and those generated just before the close to determine how a portfolio that combines both signals performs.
We will proceed by providing an overview of the signals, establishing the portfolio assumptions, presenting the results of a portfolio built using the 60 minute signal, presenting the results of a portfolio that trades both the 60 minute and close signals, and discussing the findings.
To recap for new readers, Leapday’s REACTION signals are available for 3 entry points after an event day, which is the first day the market is open subsequent to a company’s earnings announcement. These 3 entry points are: (1) 60 minutes after the open on the event day; (2) just before the market close on the event day; (3) before the market open on the next trading day after the event day. As mentioned in the previous section, the study will focus on the signals from 60 minutes after the open on the event day. This signal is available for 3 holding periods: 2d, 3d, and 4d. We use the 3d hold signal in the portfolio construction below.
The REACTION signals range from -100 to +100 indicating the direction and magnitude of the signal. Like our previous report using the close signals, we will use approximately the top one-third of signals ordered by signal magnitude. This approach provides a balance between using the strongest signals and having enough trading activity to utilize available capital. Table 1 below shows the number of signals these settings correspond to between 2016 and 2020. With this constraint we observe over 1,000 trades a quarter.
As outlined in the previous section, we will use the strongest one-third of REACTION signals that are released 60 minutes after the open on the first day the market is open subsequent to a company’s earnings announcement to build a simulated portfolio. We will focus on the 3d hold signal. Below are all the assumptions used in our portfolio construction.
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 minutes) and exit the trade on the close 3 days later (t2 close).
For the entrance price we use the midpoint of the spread at the time the signal is generated. Because it would not be realistic to trade at the midpoint for many of these trades we add additional trade cost assumptions (below).
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 and 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 trade value per position (trade value is based on trailing 20 day average traded value in the ticker).
Beyond the two constraints on trade size stated above, trade equal weight.
Round-trip trading costs are based on breakpoints for liquidity groups as follows. We have doubled trading costs from our previous report (that trades at the close) in order to adjust for trading earlier in the day when markets are less liquid and spreads are wider:
Low (<$3M historical average trade value): 40 bps
Mid ($3M-$25M historical average trade value): 20 bps
High (>$25M historical average trade value): 10 bps
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
Below we present metrics from a portfolio that trades the top one-third of the t0 open + 60 minute 3d signal and holds those trades for 3 days using the portfolio assumptions stated above.
The metrics associated with the chart above are as follows. We include metrics without costs (Table 2) and with costs (Table 3). While volatility from the pandemic in 2020 saw a dip in performance for the open + 60 minute signal, the signal has begun to perform well again since Q4 of 2020 and overall metrics from 2016 to 2020 remain strong.
Below in Table 4 are additional metrics for the portfolio between 2016 and 2020 including maximum drawdown and correlation to the broader market.
It is worthwhile to note that the above metrics for annual return are based on constant capital in which trade size does not grow with the portfolio and instead is based on the starting capital. There is no reinvestment of profits. When we present annual portfolio growth metrics above, this is inherently understating the annual return because the return is calculated using cumulative portfolio value while trade sizing is held constant (e.g. - the 2018 portfolio annual return is based on growth of portfolio since the end of 2017, not the starting capital in January 2015 that the trade size is based on). Below in Table 5 we present annual metrics based on the constant capital used.
One additional caveat to note is that the majority of events take place during a few weeks toward the middle of each quarter. Therefore a portfolio trading these signals will be in mostly cash during the beginning and end of each quarter. Table 6 below shows that the median day uses only 20% of the initial capital. Thus, annualized returns presented above are conservative for a portfolio setting since an investor would have significant capital to deploy into additional strategies during much of the year and return on capital used is significantly higher.
Finally, all the metrics presented above do not filter out any companies based on market capitalization or trade value. Given the starting portfolio size and the restrictions on the portfolio construction that cap how much of a company’s trade value can be traded, lower liquidity companies do not have a significant impact on the total return. However, to give additional reassurance of the value of the REACTION signals across high liquidity companies, we present metrics below in Tables 7 - 9 for a portfolio that only trades companies with an average daily trade value over $25M using all the same assumptions as before.
As shown above, constraining trades to only highly liquid companies results in only a small deterioration in annualized returns. In fact some metrics, like 2020 performance and max drawdown, improved after removing low liquidity companies from the portfolio.
This report built a portfolio with the t0 open + 60 minute signal and our previous report built a portfolio using the t0 close signal. While both portfolios held trades for 3 days, the exits were different (t2 close for the t0 open + 60 minute signal and t3 close for the t0 close signal). The natural next step is to combine these into one portfolio and examine performance.
The first step we take is examine the correlation between the return streams of the two portfolios. Table 10 below shows this correlation.
A correlation of 0.41 suggests that the two return streams are different enough that we may be able to create a stronger portfolio by combining the two portfolios. We should also note that this statistic is overstated since lighter activity days will naturally be more correlated because on these days the portfolio is mostly in cash and returns are near zero.
Below we present metrics from a portfolio that trades the top one-third of the t0 open + 60 minute 3d signal and holds those trades for 3 days and also trades the top one-third of the t0 close 3d signal and holds those trades for 3 days. The former uses the portfolio assumptions above and the latter uses the portfolio assumptions from our previous report. The assumptions are almost identical and the primary distinction is that trading costs are doubled for the t0 open + 60 minute signal to account for using the midpoint of the spread at the time the signal is generated for the entry price.
Metrics associated with the chart above are presented below in Tables 11 - 14.
As the tables above indicate, performance of the combined portfolio is better than either individual portfolio. Between 2016-2020 and inclusive of trading costs, the t0 open + 60 minute signal portfolio returned 8.8% annualized, had a Sharpe ratio of 1.69, and a max drawdown of -9.1%. As shown in our previous report, the t0 close signal portfolio returned 11.0%, had a Sharpe ratio of 1.90, and a max drawdown of -3.8%. The new combined portfolio exhibits better risk-adjusted metrics with an annualized return of 9.9%, a Sharpe ratio of 2.14, and a max drawdown of -3.5%. The result corroborates our previous observation that the low correlation of return streams from the individual portfolios creates a superior combined portfolio.
We have demonstrated that building a market-neutral portfolio based on trading Leapday’s REACTION signals that are released 60 minutes after the open on the first day the market is open after an earnings announcement produces strong annual returns, high Sharpe ratios, and small drawdowns.
In a previous report, we showed that trading the REACTION signals released just before the close on the first day the market is open after an earnings announcement also produces strong portfolio metrics. In this report, we showed that the REACTION signals released 60 minutes after the open and those released just before the close have a low correlation of returns. Thereby, when combined into a single portfolio, risk-adjusted portfolio metrics improve over either standalone portfolio with a higher Sharpe ratio and lower max drawdown. We believe that these results, which are robust to trading costs and various market regimes, highlight the power of using Leapday’s REACTION signals in a strategy. Each REACTION signal is an individual prediction for a company’s short term return. Collectively, they produce a portfolio with a unique return stream when signals with multiple entry points are used.
The metrics presented above are based on a simple standalone strategy and sophisticated investors can use the signals in a variety of ways to boost performance even further. The signals can be used as an input in a model or any decision making framework alongside other inputs to outperform the standalone strategy. Furthermore, investors can use more advanced portfolio construction methods. In this study, we treat all signals that fall in the top one-third of signals equally. In our whitepaper, however, we demonstrate that the top 5% of signals outperform the top 10% and so forth. This leaves room for further boosts in performance by weighting trades appropriately. Finally, the entry and exit rules used in this portfolio are simple. The portfolio performance can be further improved by optimizing the hold to incorporate additional information gauged from the onset of the trade until the optimal exit.
In this report we build a market-neutral portfolio using signals generated after earnings announcements to profit from short-term price reactions. We focus on the REACTION t0 open + 60 minutes 3d signal, which is generated 60 minutes after the open on the first day of trading subsequent to a company’s earnings announcement, and create a portfolio that uses the top one-third of these signals based on signal magnitude to enter trades 60 minutes after the t0 open and hold that trade for 3 days. Inclusive of costs, this portfolio has an annualized return of 8.8% between 2016-2020, a Sharpe ratio of 1.69, a maximum drawdown of -9.1%, and a correlation to SPY of -0.01. If trading is restricted only to highly liquid companies, metrics remain similarly strong. Between 2016-2019, annualized returns are 10.6% and the Sharpe ratio is 2.32. The pandemic-induced volatility of 2020 resulted in some deterioration of performance in that year, however Q4 of 2020 showed that the signals are performing well again and this has continued through the publication date in May 2021 (2021 metrics are not included in this report).
In this report we also create a portfolio that combines the t0 open + 60 minutes 3d signals introduced in this report and the t0 close 3d signals used in our previous report. These two sets of signals enter trades at different times (t0 open + 60minutes & t0 close), exit trades at different times (t2 close & t3 close), and have a low correlation of returns. The result is a combined portfolio that inclusive of costs has an annualized return of 9.9% between 2016-2020, a Sharpe ratio of 2.14, a maximum drawdown of -3.5%, and a correlation to SPY of 0.06. These metrics are stronger than either portfolio on its own, perform similarly well when restricted to highly liquid companies, perform well in 2020, and highlight the value of using multiple entry points from the Leapday REACTION signals.
The metrics presented in this report are conservative given the trade cost assumptions, portfolio position sizing constraints that we use, and the cyclical nature of earnings events which allows investors to deploy capital elsewhere during periods of low earnings activity. These results indicate that investors and traders can use the REACTION signal to drive an independent trading strategy or as an input for a model or decision making framework.
In Part 3 of this report, we will construct a market-neutral portfolio using the REACTION signals generated before the open on the second day of trading subsequent to a company's earnings announcement. We will then build a combined portfolio using all three of the REACTION entry points. To read Part 3, click here.
This material 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.