QuantDesk® Machine Learning Forecast
for the Week of April 9th, 2018
Even Machines Need Us To Cut Them Some Slack
by Erez Katz, CEO and Co-founder of Lucena Research.
As investment professionals looking to capitalize on unique data and clever predictive algorithms, it is incumbent upon us to understand how machines learn and subsequently put forth the proper conditions for a successful outcome. Setting unrealistic expectations will most likely prematurely terminate a perfectly sound and profitable algorithm. If, for example, we were to ask the machine to predict the next jackpot’s winning numbers, we are probably setting it up for failure. Today, I’d like to touch on a few important guidelines that will help you build gradually on small successes and ultimately maximize the benefit from the data and the algorithm.
Review Of How Deep Learning Works For Price Forecasting
The concept behind deep learning can be described in the context of solving the following problem. Given the following feature values for Apple (APPL) on a particular day, determine Apple’s price change 21 days later:
- Feature 1 - (F1) PE Ratio
- Feature 2 - (F2) Social Media Sentiment Score
- Feature 3 - (F3) Average Analysts Recommendations Score
- Feature 4 - (F4) Last reported EBITDA to sales ratio
Score = (W1*F1 + W2*F2 + W3*F3 + W4*F4). The weights, W1 to W4, are merely there to assess how important should one feature be over another in a particular scenario. That’s truly the crux of the problem. Given the approximately 850 factors that we hold in our database, each tasked with a descriptive value for every stock in our universe on a particular day, which combination of factors are most relevant and how much weight should be association with each factor (F-1 to F-850) in order to assess the most predictive score.
Deep learning tries to solve the problem mathematically by constructing a complex multi-variable formula and adjusting the variables based on how far off the formula’s outcome was from the actual outcome. By feeding into the model a large amount of training data (feature values and price change outcomes, also called labeled data), the machine learns to adjust the various weights associated with the features in order to minimize a cost function which measures the difference between the correct outcome and the model’s outcome. In essence, the system goes through an iterative process by which it tries to minimize the cost function (or to narrow the gap between the formula’s outcome and the desired outcome).
If the description above is a bit abstract and hard to follow, I highly recommend watching this short video by 3Brown1Blue on YouTube. 3Brown1Blue does a terrific job simplifying the concept through a series of well-crafted, animated videos.
How To Help The Machine Succeed
So now that we understand the mechanics of machine learning, I wanted to list just a few guidelines that will help you maximize the benefits from a deep learning research project. By gaining greater understanding of the machine’s limitations, you will be better equipped to guide your research and ultimately succeed.
Isolating The Problem
It’s important to state the problem we ask the machine to solve in the narrowest form possible. Here is an example: Since the market in general is highly correlated, Apple’s price forecast is highly dependent on the overall market’s behavior. In practice, regardless of Apple’s particular state at a specific point in time, if the market drops significantly, Apple will likely drop along with the market. Perhaps training the machine to identify Apple’s price change relative to the S&P is more achievable than training Apple’s price forecast alone.
Regression vs Classification
Regression looks to solve a forecasting problem mathematically by generalizing the relationships between inputs X with outputs Y. Classification is the process by which the input is inferred from the outcome. By grouping (clustering) the output, the machine can infer what common characteristics are most distinguishable between the output clusters. In certain situations, it’s easier to classify a buy/sell sentiment vs. going for a specific price change.
Input Data Scaling (Normalizing Input Factors)
The data is the bloodline of an AI model. Normalizing all input data (as values between zero and one, for example) enables widely disparate and orthogonal data sources to be represented in a homogenous way. This makes the cost minimization process more easily achievable. Gradient descent and back propagation are great examples of how the deep learning process tweaks the weights and biases in order to speed up the error reduction process (as derived from the cost function) and subsequently speeds up the learning process.
Defining An Objective Function
The objective function will ultimately determine how to activate the output neuron. It is important to clearly state what we’re looking for. For example, if the output neuron gets a score of 0.50 (on a range of 0 to 1), it’s important to predetermine if 0.50 is enough to activate the neuron. In many cases we want the machine to learn to distinguish between a meaningful actionable score, a random score or an insignificant score. In a trading situation, having a positive buy signal may not be enough since buying a stock with small returns, though still positive, may not be enough to overcome transaction costs.
With all the incredible power and perceived complexity of machine learning we must gain a high-level understanding of the logistics under the hood. We mustn’t treat deep learning as some sort of a magical concept. By demystifying deep learning we will be better equipped to unleash its full potential and benefit from it.
As in the past, we will provide weekly updates on how the model portfolios and the theme-based strategies we cover in this newsletter are performing.
Tiebreaker has been forward traded since 2014 and to date it has enjoyed remarkably low volatility and boasts an impressive return of 49.53%, low volatility as expressed by its max-drawdown of only 6.16%, and a Sharpe of 1.65! (You can see a more detailed view of Tiebreaker’s performance below in this newsletter.)
BlackDog – Lucena’s Risk Parity - YTD return of -5.51% vs. benchmark of -2.04%
We have recently developed a sophisticated multi-sleeve optimization engine set to provide the most suitable asset allocation for a given risk profile, while respecting multi-level allocation restriction rules.
Essentially, we strive to obtain an optimal decision while taking into consideration the trade-offs between two or more conflicting objectives. For example, if you consider a wide universe of constituents, we can find a subset selection and their respective allocations to satisfy the following:
- Maximizing Sharpe
- Widely diversified portfolio with certain allocation restrictions across certain asset classes, market sectors and growth/value classifications
- Restricting volatility
- Minimizing turnover
We can also determine the proper rebalance frequency and validate the recommended methodology with a comprehensive backtest.
Forecasting the Top 10 Positions in the S&P
Lucena’s Forecaster uses a predetermined set of 10 factors that are selected from a large set of over 500. Self-adjusting to the most recent data, we apply a genetic algorithm (GA) process that runs over the weekend to identify the most predictive set of factors based on which our price forecasts are assessed. These factors (together called a “model”) are used to forecast the price and its corresponding confidence score of every stock in the S&P. 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 the new model and the top 10 positions assessed by Lucena’s Price Forecaster.
The top 10 forecast chart below delineates the ten positions in the S&P with the highest projected market-relative return combined with their highest confidence score.
To view a brief video of all the major functions of QuantDesk, please click on the following link:
The table below presents the 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).
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: Tiebreaker is an actively managed long/short equity strategy. It invests in equities from the S&P 500 and Russell 1000 and is rebalanced bi-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 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. On September 28, 2016 we have applied new allocation algorithms to Tiebreaker and modified its rebalancing sequence to be every two weeks (10 trading days). 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: 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: firstname.lastname@example.org 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.
If you have any questions or comments on the above, feel free to contact me: email@example.com
Have a great week!
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 neither manages funds nor functions as an 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 on historical data analysis.
Past performance does not guarantee future success. In addition, the assumptions and the historical data based on which opinions are 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.
The performance results for active portfolios following the screen presented here will differ from the performance contained in this report for a variety of reasons, including differences related to incurring transaction costs and/or investment advisory fees, as well as differences in the time and price that securities were acquired and disposed of, and differences in the weighting of such securities. The performance results for individuals following the strategy could also differ based on differences in treatment of dividends received, including the amount received and whether and when such dividends were reinvested. Historical performance can be revisited to correct errors or anomalies and ensure it most accurately reflects the performance of the strategy.