QuantDesk® Machine Learning Forecast
for the Week of April 16th, 2018
Data Science: A Prerequisite To Machine Learning
by Erez Katz, CEO and Co-founder of Lucena Research.
With the proliferation of big data, many have been quick to hang the “AI shingle” on their doors. Being an AI player would typically earn you a new level of professional esteem by prospects, clients, and investors, but big data and AI is no longer a privilege of the fortunate few. Complex concepts in deep learning are now more accessible than ever before. Take, for example, solving image recognition problems with deep learning. Remarkably, you can gain approximately 97% accuracy of hand writing recognition with as little as 75 lines of code in Python on TensorFlow. Thanks to the great work done by our friends at Google Brain and Google’s Deep Minds, complex deep learning solutions are easily deployed through open source libraries.
As many seek to enter alternative data and deep learning into their research continuum, they are quick to realize that throwing data at a deep learner is not enough to solve real-world problems. The reality is that data science is essential to commercially sound deep learning solutions, and today I want to cover just a few concepts that will help guide you as you consider your entry into quantitative investment research.
Labeled vs. Unlabeled Data
Unlabeled data consists of observations that can be obtained relatively easily from the world around us. The data is mainly a collection of items without any classification or identification. Social media tweets, news feeds, corporate actions, sales figures, and location data are all considered in their natural form to be unlabeled data. In contrast, labeled data is unlabeled data augmented with some sort of identification (also called classification or tagging).
The additional information overlaid on unlabeled data is mainly human-driven, and therefore more costly and harder to obtain. For example, labeling a photo to distinguish whether it contains a dog or a cat must be informed initially by humans. The process of deep learning is empowering a machine to infer the proper label from new unlabeled data by generalizing the relationship between the data (attributes or features) and its labels. Machine learning is made available through “inspecting” lots and lots of labeled data in order to discern the underlying association rules. Subsequently when the machine is presented with new unlabeled data it can label it on its own with a high degree of certainty (measured by accuracy and precision).
The process of mapping and labeling raw data so that it is most effective for a deep learner is not simple. It requires deep domain expertise in the underlying business that sources the data. In addition, in most cases the data is not directly related to the financial markets and it needs to be aggregated or arranged in a certain way so that it’s most relevant to tradeable securities.
Imagine you have a five-year history of every mobile sales transaction at Starbucks. Even the most obvious use of such information, if not done properly, will not be predictive. A natural approach would likely be to correlate total sales to Starbucks’ future stock price since strong sales will most likely drive the next quarterly earnings. However, if the sales figures are not seasonally adjusted, or not measured in the context of a change against a predetermined moving average, the information will be less exploitable by the deep learner. In addition, there are additional hidden gems in Starbuck’s sales data that only an astute data scientist can recognize. Take, for example, aggregating Starbucks sales by geographic location or consumer demographic profile. There may by additional valuable information to infer from a positive Starbucks sales trend regarding things like consumer confidence, discretionary spending forecast, or the sales forecast of supply chain dependencies.
IID Data – Independently and Identically Distributed Data
Labeled data is most effective for a deep learner when its values are independent of each other and are similarly distributed. The reality, however, is that most time-series data (the type of data mostly used for price forecasting) are actually dependent. It is incumbent upon the data scientist to map the training data into an IID-like structure for a most efficient deep learning process.
Suppose you are investigating how heart rate can predict if a person is a smoker. You can measure BPM (beats per minute) as 30 samples of one-minute (30*1m) readings and ask if the person smokes in order to build your label dataset. What would contribute to a better predictor?
- 30 observations from one person who smokes?
- or one observation from 30 people who smoke?
Given that one person's heart rate won't change much over 30m, it seems clear that you'd rather have one-minute samples from 30 different people rather than 30-minute samples from one person. To put this in context, 30 observations from different people are independent and identically distributed while 30 readings from the same person are highly dependent. An astute data scientist should know how to map a sample data into an IID format in order to provide the machine with the most conducive conditions to learning.
The examples above should put some context into what it takes to make alternative data and deep learning jive. At Lucena, we find ourselves in a unique position as an intermediary between alternative data providers and buy-side data intelligence seekers. We have systemized the life cycle of taking raw data and converting it into actionable and consumable products. Our process includes:
- Consumption of raw data
- Data validation
- Data enhancement with feature engineering and proper labeling
- Training predictive models through deep learning technology
- Cross validation
- Out of sample backtesting
- Delivery of derived signals in multiple consumable formats:
- Data Feeds
- Model Portfolios
- Custom Research
If you are looking to incorporate alternative data into your investment research, feel free to reach out to me and I will gladly answer any questions or direct you to one of our quants or data scientists for further assistance.
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 50.16%, low volatility as expressed by its max-drawdown of only 6.16%, and a Sharpe of 1.66! (You can see a more detailed view of Tiebreaker’s performance below in this newsletter.)
BlackDog – Lucena’s Risk Parity - Since Inception 38.99% vs. benchmark of 29.19%
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.