QuantDesk® Machine Learning Forecast
for the Week of October 5
Analysis
This week marks Tiebreaker’s one-year anniversary since we started to live trade it based on its present execution format. Coincidentally, this week also serves as a perfect example as to why Tiebreaker is such an exciting strategy and why it exemplifies how critical is predictive analytics for active management. Tiebreaker ended the week at another all-time high, rising by +1.07%, but that’s just part of the story. On Friday, the disappointing September employment report initially spurred a broad-market selloff, only to reverse later due to bargain hunters, and the prospect that the Feds will stay away from raising rates this year. The Dow posted its biggest one-day reversal in four years, as it swung from a drop of over -250 points to close higher by about +200 points. Tiebreaker was in the green during the market selloff and during its dramatic up-turn reversal. In other words, during the market selloff, Tiebreaker was positive since its gains from its short positions outweighed the losses from its long positions. Conversely, during the market reversal the gains from Tiebreaker’s long positions surpassed its losses from its short holdings.
Image 1: Last week’s change and Year to date gains.
Since 9/1/2014, Tiebreaker’s model portfolio is up +26.86% with a Sharpe of 3.22. Year-to-date, Tiebreaker is up 15.30% with a Sharpe of 2.74. There is an additional inherent psychological benefit to a well-hedged long/short strategy. On the days in which the S&P futures were pointing toward a dramatically lower open, our Tiebreaker subscribers were relatively calm knowing that they are somewhat protected or well hedged. Furthermore, in our case the volatility actually presented an opportunity for profit. Below I elaborate more about Tiebreaker and how it came to be.
BlackDog, Lucena’s tactical asset allocation strategy, also enjoyed an excellent week as it ended higher by +1.93%, better than the S&P 500 by +89 bps.
BlackDog: Model portfolio performance compared to the S&P 500 from 4/1/2014 to 10/2/2015.
Past performance is no guarantee of future returns.
Tiebreaker: Model portfolio performance compared to S&P 500 and the Vanguard Market Neutral Institution fund VMNIX from 9/1/2014 to 10/2/2015.
Past performance is no guarantee of future returns.
Tiebreaker’s History
The impetus to design a model strategy was in an attempt to validate our flagship platform QuantDesk®. When we launched QuantDesk® during the 4th quarter of 2013, we were often faced with hesitant prospective clients who loved the product but questioned its track record and efficacy. Moreover, many of those prospects could not easily visualize how to integrate QuantDesk’s modules into their internal research discipline. We wanted to create a single strategy that takes advantage of all of QuantDesk’s modules. Specifically:
- Price Forecaster
- Portfolio Optimizer
- Hedger
- Event Analyzer
- Backtester
We initially deployed Tiebreaker on April 2014 as a market neutral and beta neutral strategy. We soon realized that the strategy was doing a fairly good job in protecting the portfolio from market volatility. However, the initial deployment didn’t generate alpha at the time due to its beta or cash neutral tendency to preserve a low volatility portfolio. The problem with the above approach was its difficulty in generating alpha during a protracted period of Fed induced low-vol bull market. Apparently, 86% of all active managers have underperformed the major index benchmarks during 2014. We quickly modified Tiebreaker to introduce more dynamic hedging techniques. We wanted our hedge positions to be sensitive to market and stock specific volatility. The idea was to dynamically tilt the long/short exposure in order to take advantage of bullish trends while protecting the portfolio from unexpected moves when the market turns volatile.
See below Tiebreaker in its initial format during its first 4 months and the dramatic change since 9/1/2014.
Image 2: Tiebreaker evolution from market neutral/beta neutral to long/short exposure tilt.
We then reassessed the strategy and applied the following changes:
- Beta-neutrality was revoked and directional tilts allowed.
- Maximum position size was limited to prevent over exposure to a single position.
- Total positions were reduced from 20 per week to 10 per week.
- Profit target and stop-loss levels were widened to allow more time in the market.
- Exited positions were no longer replaced with alternatives, but rather held in cash until the next rebalance.
Below is a general description of Tiebreaker as it is traded today:
How do we pick constituents?
- Identify positions from QuantDesk’s Event Study bullish scans.
- Further hone in on the top holdings using QuantDesk Price Forecaster.
- Optimize the long leg with QuantDesk’s mean-variance optimizer.
- Use QuantDesk’s Hedge Finder to identify long or short anti-correlated constituents to preserve the return of the long leg, but with lower volatility.
How do we execute?
- Positions are held for one week [five trading days], or until exit conditions are met.
- Entry and exits are executed through market, VWAP and MOC orders.
- All open positions are controlled by order-cancel-order (OCO) exit conditions, trailing stop loss and target gain.
Results:
- Long tilt has been dominant and has been generating returns during bull markets
- Drawdown and volatility have been muted during market corrections.
Image 3:Tiebreaker has been able to avoid major drawdown during market corrections
What are Tiebreaker strengths?
- Low correlation to the market
- Highly liquid constituents
- Active and agile, with timely responses to changes in market sentiment
- Machine learning optimized for maximum return / minimum volatility
- Quantitative driven, self adjusts to market and stock-specific technical, fundamental and other conditions
What are the risks?
- Exogenous risk or black swan event affecting equity markets
- Stock-specific liquidity risk causing gaps beyond stop loss
- Protracted high-volatility, down trend equity environment
- Inability to borrow [short] certain stocks
- Transaction costs: High turnover and exposure to dividend and interest owed on short positions
How does Tiebreaker mitigate the outlined risk?
- Enforce maximum position size per equity
- Trailing stop loss [GTC] placed on every open position
- Realize return early and protect from sudden moves via order-cancel-Order (OCO) on each position
- Unique hedging algorithm finds optimal offset for long positions
- Profitable positions are left in cash, exposure reduced
- Directional tilts are allowed but reassessed every week
- Entry via VWAP during active trading hours to provide acceptable depth for trades
- Exit at close [MOC] reduces slippage and adds liquidity
- Deep discount brokerage mitigates drag of high-turnover
- All statistics based on non-levered account
- Backtest hit rate is 63%
- Highly liquid large caps and mega caps with low slippage and easy to short.
Lastly, I wanted to share with you how a live portfolio tracks Tiebreaker’s model portfolio performance. See below two performance reports side by side:
Left: QuantDesk® model portfolio’s performance report
Right: Interactive brokers’ live performance report
Appendix
For those of you unfamiliar with BlackDog and Tiebreaker, here is a brief overview:
BlackDog and Tiebreaker are two out of an assortment of model strategies that we deploy for our clients. Our team of quants is constantly on the hunt for innovative investment ideas. Lucena’s model portfolios are a byproduct of some of our best research, packaged into consumable model-portfolios. The performance stats and charts presented here are a reflection of live portfolios tracked on our platform, QuantDesk®. Actual performance of our clients’ portfolios may vary as it is subject to the manager’s discretionary implementation. We will be happy to facilitate an introduction to one of our clients for those of you interested in reviewing live brokerage accounts that track our model portfolios.
BlackDog:
BlackDog is a tactical asset allocation strategy that utilizes highly liquid ETFs of large cap and fixed income instruments. The portfolio is adjusted approximately once per month based on Lucena’s Optimizer in conjunction with Lucena’s macroeconomic ensemble voting model. Due to BlackDog’s low volatility (half the market in backtesting) we leveraged it 2X. By exposing twice its original cash assets, we take full advantage of its potential returns while maintaining market-relative low volatility and risk. As evidenced by the chart below, BlackDog 2X is substantially ahead of its benchmark (S&P 500).
Tiebreaker:
Tiebreaker is an actively managed market-neutral long/short equity strategy. It invests in equities from the S&P 500 and Russell 1000 and is rebalanced weekly using Lucena’s Forecaster, Optimizer and Hedger. Tiebreaker splits its cash evenly between its core and hedge holdings, and its hedge positions consist of long and short equities. Tiebreaker has been able to successfully avoid major market drawdowns while still taking full advantage of subsequent run-ups. The main factor that has enabled Tiebreaker to perform so well is its ability to adjust its long/short exposure based on idiosyncratic volatility and risk. Lucena’s Hedge Finder is primarily responsible for driving this long/short exposure tilt.
I designed, backtested and deployed Tiebreaker utilizing QuantDesk® exclusively. This can serve as an example of how a portfolio manager can take full advantage of Lucena’s technology.
In the past year, we covered QuantDesk’s Forecaster, Back-tester, Optimizer, Hedger and our Event Study. In future briefings, we will keep you up-to-date on how our live portfolios are executing. We will also showcase new technologies and capabilities that we intend to deploy and make available through our premium strategies and QuantDesk® our flagship cloud-based software.
My hope is that those of you who will be following us closely will gain a good understanding of Machine Learning techniques in statistical forecasting and will gain expertise in our suite of offerings and services.
Specifically:
- Forecaster - Pattern recognition price prediction
- Optimizer - Portfolio allocation based on risk profile
- Hedger - Hedge positions to reduce volatility and maximize risk adjusted return
- Event Analyzer - Identify predictable behavior following a meaningful event
- Back Tester - Assess an investment strategy through a historical test drive before risking capital
Your comments and questions are important to us and help to drive the content of this weekly briefing. I encourage you to continue to send us your feedback, your portfolios for analysis, or any questions you wish for us to showcase in future briefings.
Send your emails to: [email protected] and we will do our best to address each email received.
Please remember: This sample portfolio and the content delivered in this newsletter are for educational purposes only and NOT as the basis for one’s investment strategy. Beyond discounting market impact and not counting transaction costs, there are additional factors that can impact success. Hence, additional professional due diligence and investors’ insights should be considered prior to risking capital.
For those of you who are interested in the spreadsheet with all historical forecasts and results, please email me directly and I will gladly send you the data.
If you have any questions or comments on the above, please do not hesitate to email me directly.
Have a great week!
To conduct your own research on QuantDesk® please use the following links.
On Bloomberg:
APPS QFORE
APPS QOPTIM
APPS QHEDGE
APPS QEVENT
On The Web:
quantdesk.lucenaresearch.com
About Lucena Research
Lucena Research brings elite technology to hedge funds, investment professionals and wealth advisors. Our Artificial Intelligence decision support technology enables investment professionals to find market opportunities and to reduce risk in their portfolio.
We employ Machine Learning technology to help our customers exploit market opportunities with precision and scientifically validate their investment strategies before risking capital.
Disclaimer Pertaining to Content Delivered & Investment Advice
This information has been prepared by Lucena Research Inc. and is intended for informational purposes only. This information should not be construed as investment, legal and/or tax advice. Additionally, this content is not intended as an offer to sell or a solicitation of any investment product or service.
Please note: Lucena is a technology company and not a certified investment advisor. Do not take the opinions expressed explicitly or implicitly in this communication as investment advice. The opinions expressed are of the author and are based on statistical forecasting based on historical data analysis. Past performance does not guarantee future success. In addition, the assumptions and the historical data based on which an opinion is made could be faulty. All results and analyses expressed are hypothetical and are NOT guaranteed. All Trading involves substantial risk. Leverage Trading has large potential reward but also large potential risk. Never trade with money you cannot afford to lose. If you are neither a registered nor a certified investment professional this information is not intended for you. Please consult a registered or a certified investment advisor before risking any capital.