QuantDesk® Machine Learning Forecast

for the Week of November 7

Friday’s jobs report recorded the addition of 161K new jobs in October as the unemployment rate dropped to 4.9% and seasonally adjusted hourly wages were up by 2.8%. By all measures, this is good news as it indicates that the economy is continuing to strengthen. On the other hand, the market is off by more than 5% from its all-time highs recorded in August, and Friday marked the S&P’s 9th consecutive down day. Many attribute the recent drop to pre-election jitters and a strengthening conviction of a Fed rate hike in December.

Volatility, as measured by the Chicago Board Options Exchange Volatility Index (VIX), jumped to 22.51 from 16.55 a week ago, a 39.04% jump!

Image 1: VIX October 31st to November 4th – Source: Google Finance
Past performance is not indicative of future returns.

Oil prices fell sharply amid doubts that OPEC will be able to reach an agreement to limit production, and on reports of a large rise in US crude inventories. West Texas Intermediate crude fell to $44.13 per barrel from $49.25 a week ago.

Image 2: USO October 31st to November 4th – Source: Google Finance
Past performance is not indicative of future returns.

Using Lucena’s one-week Price Forecaster, we estimate crude oil to trade slightly higher by 43 bps, but with 2.14% volatility.

Image 3: USO next week’s price forecast. Estimated to rise by 43bps within 2.14% price volatility and with an 88.16% confidence score.

Forecasting the Top 10 Positions in the S&P

Lucena’s Forecaster uses a predetermined set of factors (normally 10 factors) that are selected from a large set of over 450 factors, using a genetic algorithm (GA) process that runs over the weekend. These factors (together called a “model”) are used to determine the forecasted price of every stock in the S&P and their corresponding confidence score. Our machine-learning algorithm travels back in time over a look-back period (or a training period) and searches for historical states in which the underlying equities were similar to their current state. By assessing how prices moved forward in the past, we anticipate their projected price change and forecast their volatility.

The charts below represent this week’s model and the top 10 positions assessed by Lucena’s Price Forecaster.

Image 4: Default model for the coming week

The top-ten forecast chart below delineates the ten positions in the S&P with the highest projected return combined with the highest confidence score.

Image 5: Forecasting the SPY for the coming week.
The yellow stars (0 stars meaning poorest and 5 stars meaning strongest) represent the confidence score based on the forecasted volatility, while the blue stars represent backtest scoring as to how successful the machine was in forecasting the underlying asset over the lookback period — in our case, the last 3 months.

To view a brief introduction video of all the major functions of QuantDesk, please click on the following link:

Dynamic Models Usher In a New Generation of Successful Strategies

It is exciting to see how quantitative analysis has evolved over the years. It started in academia with published research on technical analysis for investment in the 1980’s. Those who were quick to adopt it in the 1990’s profited handsomely by deploying active strategies predicated on that very research. As technical analysis became more prevalent, profits were quickly eroded since more investment professionals were keen on exploiting the same signals. In recent years, we witnessed the proliferation of big data and machine learning intelligence into many aspects of our lives. Consequently, the lifespan of a profitable quant-based investment strategy has become shorter and the investment competitive advantage became short lived. The fundamental survival rules of quant-based funds depended on their ability to be nimble. Moreover, successful funds were forced to keep reinventing themselves and constantly hunt for new sophisticated investment techniques not easily reproducible by their competition.

Today, I want to give you a quick glimpse into Lucena’s next generation strategies and what makes them unique. There are really two main qualities that make a strategy unique:

  1. A unique predictive data source.
  2. Novel techniques used to exploit such data.

In a previous posting I wrote about Lucena’s FRX strategy. Today, I want to share with you how we deploy our unique method geared to evaluate models dynamically. The dynamic model in today’s example is derived from unsupervised learning techniques. Rather than defining rules of success and training the machine through a supervised process by which we reward or “punish” conditions in history that constituted a desired or undesired outcome, unsupervised learning looks at data through clusters or statistical density estimation.

Our FRX strategy evaluates the data perpetually and, based on the most recent data, it creates the rules by which daily signals are generated.

The image below represents the average currency value of 10 currencies (G-10) over an 8-year period. As can be seen, contrary to the equity market, a buy and hold strategy will not be a good approach for the underlying currency pairs as over time the values mainly stay flat. However, the data clearly presents short term opportunities for arbitrage.

Image 6: G-10 average daily NAV between 2008 and 2016.

Our ML classification process evaluates which macroeconomic indicators, in conjunction with foreign exchange technical indicators, should be considered to construct the model. Then based on the selected model, it decides which currency pairs to enter a position in.

We run thousands of cross validation assessments in order to evaluate optimal conditions in-sample that persist out-of-sample.

Image 7: Cross validation process to evaluate in-sample conditions that persist out-of-sample.

Our cross validation uses Lucena’s Event Analyzer to identify which factors should be used in today’s model.

Image 8: Applying an event study in order to evaluate which factors and thresholds revealed in-sample, persist out-of-sample.

We then use the selected factors to conduct our daily positions evaluation.

Image 9: Daily evaluation process by which event signals are used to find out which currency pairs to trade. Specifically, in this example we look at long term macroeconomic data (3 months) combined with shorter term FRX technical data (1 week).

Finally, I want to share with you how effective this technique has been through backtesting and live trading.

Image 10: FRX backtest from 1/1/2008 to 6/2016. 1x leverage.
Past performance is not indicative of future returns.

Image 11: FRX live trades from 8/1/2016 to 11/4/2016. Results expressed in 1x exposure. Most FRX strategies apply leverage beyond the demonstrated exposure. As an example, with 10x leverage, returns would be translated to 32.9% with a max drawdown of 8.8%, well within the risk bounds of the S&P.
Past performance is not indicative of future returns.


The table below delineates a trailing 12-month performance and a YTD comparison between the two model strategies we cover in this newsletter (BlackDog and Tiebreaker), as well as the two ETFs representing the major US indexes (the DOW and the S&P).

Image 6: Last week’s changes, trailing 12 months, and year-to-date gains/losses.

Past performance is no guarantee of future returns.

Model Tiebreaker: Lucena’s Active Long/Short US Equities Strategy:

Tiebreaker: Paper trading model portfolio performance compared to the SPY and Vanguard Market Neutral Fund from 9/1/2014 to 11/4/2016.
Past performance is no guarantee of future returns.

Model BlackDog 2X, Lucena’s Tactical Asset Allocation Strategy:

BlackDog: Paper trading model portfolio performance compared to the SPY and Vanguard Balanced Index Fund from 4/1/2014 to 11/4/2016.
Past performance is no guarantee of future returns.


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 offer 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 paper traded portfolios on our platform, QuantDesk®. Actual performance of our clients’ portfolios may vary as it is subject to slippage and the manager’s discretionary implementation. We will be happy to facilitate an introduction with one of our clients for those of you interested in reviewing live brokerage accounts that track our model portfolios.

Tiebreaker is an actively managed 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 avoid major market drawdowns while still taking full advantage of subsequent run-ups. Tiebreaker is able 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.

Tiebreaker Live Interactive Brokers Portfolio Performance
Live performance reports are taken from an interactive brokers account which attempts to follow Tiebreaker’s model closely with the following potential differences:

  • Transactions Fees – Performance is net of transactions fees.
  • Management Fees – Performance is net of management fees.
  • Manager’s discretion – Manager can use own discretion as to final trade executions. For example, employing VWAP (volume weighted average price) and/or manually monitoring exit during stop loss and target gain.
  • Hard to borrow and restricted stocks – Hard to borrow, and restricted stocks may be substituted with highly correlated alternatives.
  • Dividends, interest or any other credits are reinvested.
  • Slippage – Depending liquidity, large block purchases could impact certain stock prices unfavorably.

Tiebreaker Model Portfolio Performance Calculation Methodology
Tiebreaker’s model portfolio’s performance is a paper trading simulation and it assumes opening account balance of $1,000,000 cash. Tiebreaker started to paper trade on April 28, 2014 as a cash neutral and Bata neutral strategy. However, it was substantially modified to its current dynamic mode on 9/1/2014. Trade execution and return figures assume positions are opened at the 11:00AM EST price quoted by the primary exchange on which the security is traded and unless a stop is triggered, the positions are closed at the 4:00PM EST price quoted by the primary exchange on which the security is traded. In the case of a stop loss, a trailing 5% stop loss is imposed and is measured from the intra-week high (in the case of longs) and low (in the case of shorts). If the stop loss was triggered, an exit from the position 5% below, in the case of longs, and 5% above, in the case of shorts. Tiebreaker assesses the price at which the position is exited with the following modification: prior to March 1st, 2016, at times but not at all times, if, in consultation with a client executing the strategy, it is found that the client received a less favorable price in closing out a position when a stop loss is triggered, the less favorable price is used in determining the exit price. Since March 1st, 2016, all trades are conducted automatically with no modifications based on the guidelines outlined herein. No manual modifications have been made to the gain stop prices. In instances where a position gaps through the trigger price, the initial open gapped trading price is utilized. Transaction costs are calculated as the larger of 6.95 per trade or $0.0035 * number of shares trades.

BlackDog is a paper trading simulation of 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).

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.


  • 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: info@lucenaresearch.com 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, feel free to contact me: erez@lucenaresearch.com

Have a great week!

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.