Erez Katz, Lucena Research CEO and Co-founder
Why Defense Contractors?
From a macro perspective, it’s no secret that the Trump administration is keen on strengthening our air defense and military. Possible tension with North Korea, Iran, Russia and China, and the middle east is forcing the United States to strengthen its military might for any contingency around the world.
In 2014, NATO members pledged to spend 2% of their GDP on defense. The administration has been and continue to press NATO to comply. As of today, NATO estimates seven of their 29 members are meeting that threshold.
Further it is estimated that, today, non US NATO members average about 1.48% of their respective GDPs. Nonetheless, except Greece and Canada, every NATO member increased their defense spending last year.
Lastly, Trump’s new aspiration for a 6th military branch, the space force, will undoubtedly increase military spending considering both China and Russia’s aspiration for space dominance.
It is clearly evidenced that international demand for US military supply ranging from drones to missile defense technology has propped up to the benefit of publicly traded large cap defense contractor well ahead of the broad market.
For the most part, the past 3 years have been an excellent time to invest in aerospace and defense stocks. This year alone, the five largest defense contractors averaged more than 40% in YTD returns, handsomely outperforming the S&P 500 of 24%.
Image 1: Since 2016, XAR (in bluc) – SPDR Aerospace and Defense ETF’s returns were approximately double the S&P (in green). Past performance does not guarantee future returns.
Today, I want to showcase how Lucena’s Machine Learning platform, QuantDesk®, can assist in constructing an aerospace/defense portfolio geared to outperform XAR by maximizing its risk adjusted return (Sharpe Ratio).
Step 1 – QuantDesk® Portfolio Replication Engine
Using the portfolio replication technology, build a 10-position portfolio from the Russell 1000 that holds similar characteristics to those of the defense sector. We chose to represent the defense sector with XAR (Aerospace and Defense SPDR ETF).
The portfolio replication engine utilizes a unique pattern-matching technology that identifies a set of stocks with distinguishing characteristics that together perform as close as possible to a given time series.
In our case, we are looking to find a collection of securities that move in tandem with XAR. Research that would traditionally take at a minimum a few days, and in some cases weeks, can be accomplished with uncanny accuracy in less than a minute.
Image 2: Replication Wizard – takes you step-by-step through the replication engine.
The replicated results appear a few short seconds later. The time series represented by the replication engine tracks almost identically the price history of XAR.
Image 3: Visual representation of our target portfolio (in orange) tracking our target time series, XAR (in green).
What’s even more interesting is that the set of constituents is mostly defense companies. Remember, I have asked to identify securities from the Russell 1000, with no specific instructions to concentrate on defense stocks.
Step 2 Optimize Your Portfolio
Now that we have a portfolio with 20 qualified constituents, we can optimize their allocation in order to maximize the portfolio’s risk adjusted return. QuantDesk utilizes Markowitz’s Nobel prize winning approach for portfolio optimization. We utilize a Mean Variance Optimization (MVO) to scientifically define how to allocate our constituents in order to maximize the portfolio’s returns for a predetermined risk profile.
The system utilizes Lucena’s Machine Learning Price Forecaster in order to optimize the portfolio allocations for a future price target. If the price target assumes a downward pressure, the portfolio automatically adjusts to a more defensive posture and, conversely, if the target price has a strong conviction higher, the portfolio will adjust to maximize its return potential.
Image 4: Optimizing the defense portfolio. The blue line and the cone represent the current portfolio before optimization and the orange line represents the target portfolio after optimization. You can see on the right side the improvement in higher Sharpe, higher returns and lower volatility.
Step 3 Backtest to Assess How Our Portfolio Performs Over Time
Rolling back time and assessing how the portfolio performs against XAP will give us a good idea if the science indeed adds value in different out-of-sample market regimes. A simple Wizard-like set of screens will launch a backtest and generate a comprehensive performance report.
Image 5: Backtesting bi-weekly optimization of the defense portfolio from January 1, 2013 to present. The blue line represents XAP while the orange line represents our dynamically optimized portfolio. On the right side you can see the improvement in higher Sharpe, higher returns with slightly higher volatility. Transaction costs and slippage are also taken into account. Past performance is no guarantee of future returns.
As you can see from the image 5 above, the max drawdown is slightly higher than the benchmark. In order to address it, we can make use of the QuantDesk Hedge Finder. The hedge finder attempts to minimize drawdown without compromising the overall returns. It uses a unique pattern matching technology suited to identify additional securities to add to your portfolio in order to preserve return while reducing volatility.
Image 7: Lucena’s Hedge Finder looking to identify additional; securities that when added to the portfolio, attempt to preserve returns but with lower volatility. As you can see the orange line represents the combined core + hedge portfolio and although it projects slightly lower returns, it advanced the Sharpe ratio and lowers the volatility.
The image below represents our final backtest of the aerospace & defense portfolio, fully optimized and hedged.
As can be seen we’ve addressed the drawdown (lowered it to -19.62% from -27.78%) while still outperforming XAP, the benchmark.
Image 6: Adding Hedging to our backtest preserves the return but with a much reduced volatility and max drawdown. Past performance is no guarantee of future returns.
Lastly, QuantDesk has unique features by which backtests can be assessed perpetually through paper trading simulation. This mode allows the portfolio to follow the same set of rules of the backtest but into the future on a roll forward basis. Trades are published ahead of the market open in order to avoid any possible look-ahead bias.
Using QuantDesk to Maximize Thematic Investing
The defense sector remains attractive for investment. Traditional advisors are now looking to preserve their 2019’s gains with recession proof alternatives. This approach may be one to consider but more importantly with QuantDesk, even a non-technical user can take advantage of alternative data and machine learning science in order to validate their own hypotheses or come up with a new ideas altogether.
Get your free QuantDesk trial here.
Questions? Drop them below or contact us.