Schulenberg and Associates, LLC (since 1981): Originators of the Thermodynamic Approach to Stock Market Prediction

Schulenberg and Associates LLC is a company that specializes in innovative software products and solutions, and with a special emphasis on the design of numerical algorithms. Our experience with stock market timing and equity modeling began in 1987 when we added neural network capabilities to our EDES™ (Empirical Data Expert System) program. EDES/Model™ continues to be our primary tool for the generation of the many dozens of small, cascaded artificial neural networks that, along with thousands of Expert System rules, form an important part of our stock market signal generation software. Development of our Stock Strategist ™ software began in 2002, and we have been continuously publishing the daily Newsletter and market timing reports since October 2004.

Stock Portfolios: Our SUPER stock portfolios are the culmination of 19 years of developmental work. Currently, three of these are being tracked on the Collective2 website: SUPER08H Hedged Stocks, SUPER15H Hedged Stocks, and the GEMINI SSS Stable Stock System. If you subscribe to these individual Strategies on Collective2, you can trade these signals yourself, or you can set up an autotrading capability that will link to your current brokerage account, in which case the trades will be made for you automatically. The GEMINI SSS Stable Stock System portfolio is automatically traded via a linkage to an Interactive Brokers IRA account and thus provides real results with real money investments. Alternatively, if you subscribe to the Stock Strategist™ Newsletter, then you will find signals for all SUPER portfolios: SUPER05H, SUPER07H, SUPER08H, SUPER10H, SUPER12H, and SUPER15H. The Newsletter also provides many other Market signals as described below.

Market Index Strategies: Our SPYPRED5 Model generates daily signals for the S&P 500, and it is traded virtually on Collective2 as the 3x Hyperbolic SPY Strategy, and also via the low-volatility Schulenberg C2Star SP500 Strategy. Similarly, our QQQ Daily Prediction signal is currently also being tracked on Collective2, using 3x leveraged ETFs, as the 3x Hyperbolic QQQ Strategy. We do not actually recommend using leverage when trading these ETFs, and so the use of 3x ETFs is primarily a demonstration that significant gains are achievable if traders can accept the inevitable significant drawdowns. If you subscribe to the Stock Strategist™ Newsletter, then you not only have the SPY and QQQ signals, but also those for IWM and DIA. as well as stock and ETF signals, and stock portfolios, as described below.

Individual Stocks: For investors who prefer to construct their own Portfolios, our Signals Report gives current Buy and Sell signals for 1672 individual stocks and ETFs. This Report is also a standard part of a Stock Strategist™ Newsletter subscription:

Strategies and Signals Available via Newsletter Subscription (Everything at one low price)

The daily 'Strategist Newsletter Market Forecast' email with 3 attachments includes:

-- Signals for 6 SUPER stock portfolios, ranging from those holding no more than 6 stocks at a time, up to 15-stock portfolios. (Hedging with SH is optional)
(Note: SUPER Portfolios are occasionally added in different size ranges, to meet different subscriber risk tolerances. Just let us know your needs.)
-- Signals for SPY, QQQ, IWM, and DIA using high-precision Models (SPYPRED5, QQQPRED2, IWMPRED2, and DIAPRED2 models).
-- Signals for 1672 US stocks and ETFs for custom portfolio construction, or for short-term trading.

Stock Strategist Newsletter Subscription (Personal)
(For a secure transaction click the top Paypal button and then click the "Pay With Debit or Credit Card" link at the bottom of the screen)

Daily Market Direction

"Z" Market Strength Indicator for 03/08/2021: +1.00

**The Z Indicator**
Z	Interpretation
-1.00	Strongly SHORT Market
-0.75	Moderately SHORT Market
-0.50	Weakly SHORT Market
-0.25	Slightly Negative Market
0.00	Weak/Neutral/Stable/Mixed Market
+0.25	Slightly Positive Market
+0.50	Weakly LONG Market
+0.75	Moderately LONG Market
+1.00	Strongly LONG Market

The "Z" Indicator is produced by weighting the output signals from our 4 Daily Index ETF Signals for the S&P, NASDAQ 100, DOW 30, and the Russell 2000.
Its value ranges from -1.0, which is very Bearish, up to +1.0, which is very Bullish for the entire US Stock Market.
It is quantized in units of 0.25, thus producing the following range of discrete values: -1.0, -0.75, -0.50, -0.25, 0, 0.25, 0.50, 0.75, and 1.0.

Note: Our 5-stock Reference Portfolio is the smallest portfolio that we have that strikes a reasonable balance between superior annualized gain performance and maximum drawdown. Larger, and less volatile portfolios, are available by Newsletter subscription.

Trading Actions for Portfolio SUPER05H for 03/08/2021:

Slot #	Current Holding	Action	New Holding	Description
1	AXON	---	AXON	Axon Enterprise Inc
2	HFC	---	HFC	HollyFrontier Corporation
3	KLAC	---	KLAC	KLA Corporation
4	MSFT	Sell & Buy	LAMR	Lamar Advertising Co A
5	SIG	---	SIG	Signet Jewelers Limited

Predictive Stock and ETF Portfolios (Collective2)

Strategies Tracked in Collective2 (Strategies Priced Individually)

-- Nasdaq 100 Daily Prediction signal (QQQPRED2) drives the "3x Hyperbolic QQQ" strategy (see below). Uses TQQQ and SQQQ.
-- S&P 500 Daily Prediction Signal (SPYPRED5) drives the "3x Hyperbolic SPY" strategy (see below). Uses UPRO and SPXU.
-- GEMINI SSS Stable Stocks (see below) a live-traded IRA at Interactive Brokers that uses both the SUPER08H Strategy and a 'hedged' S&P Strategy (using the 2x ETFs SSO (Long) and SDS (Short)) .
-- Schulenberg C2Star SP500: A low-volatility high-performance S&P trading system that uses the 2x SSO and SDS ETFs and implements the SPYPRED5 signal.
-- SUPER08H: an 8-stock Portfolio (see below). Holds up to 8 'reliable' stocks -- or fewer as necessary to control Drawdown. Hedging with 'SH' is optional.
-- SUPER15H: a 15-Stock Portfolio (see below). Holds up to 15 'reliable' stocks -- or fewer as necessary to control Drawdown. Hedging with 'SH' is optional.

After graduating from the University of California at Berkeley (Mathematics/Physics), Craig W. Schulenberg began his software development career at the MIT Instrumentation Laboratory in Cambridge, Massachusetts (now the Charles Stark Draper Laboratory). While a member of the Apollo team, he was responsible for integrating the LM flight software builds for Apollo 11 (LUMINARY), and for the programming and testing of the Lunar Module (LM) onboard guidance computer software for the Lunar Ascent (P12), Aborts during the Lunar Descent (P70,P71), and the final phases of the lunar landing itself (P66,P67).

In addition to supporting the Apollo program, he subsequently developed Flight Software code, or algorithms, or analytical software/requirements tools, first for the Space Shuttle (STS), then for the James Webb Space Telescope (JWST), then for the Orion capsule (requirements analysis tools), and finally for the Ares I launch vehicle (Constellation program) and the follow-on Space Launch System (SLS).

Some additional biographical information can be found in Gary B. Smith's archived Real Money™ articles: On the Comp, a Bounce Then a Leg Down? and The Dow Nears Its Jump Zone.

Our Major Stock Market Prediction Innovations

Schulenberg Stock Strategist™ (SSS) "Maxwell-Boltzmann" Stock Market Timing Models

The basis for the Stock Strategist™ is an entirely new approach to viewing the stock market, that is, from a thermodynamic standpoint. In thermodynamics, the Maxwell-Boltzmann distribution describes the relationship between the absolute temperature of a gas and the percentage of molecules that will have speeds within specified limits. This relationship works both ways: given a distribution of molecular speeds you can determine the temperature of a gas, and given the temperature of a gas you can determine the molecular speed distribution. We utilize an analogous concept in determining the effective temperature of the stock market. We call this value the MTI (Market Timing Indicator), although the acronym might also be considered to stand for "Market Temperature Indicator". Instead of gas molecules we consider an ensemble of over 8500 stocks and ETFs; instead of looking at the number of gas molecules within specified speed ranges we consider the distribution of "long" holdings within a spectrum of specially designed stock portfolios (with unusual buy and sell criteria). In a way, this is Technical Analysis ... but firmly rooted in the fundamental forces that underlie the stock market.

Grail System™ Stock Timing Models

The MTI (Market Timing/Temperature Indicator) that is generated by the thermal model in our Preprocessor is used to develop customized short-term timing models for 1,000 stocks and ETFs. These Grail System™ models utilize the MTI value, multiple neural networks, as well as both traditional and proprietary technical indicators (based on price and volume), in order to generate daily buy/sell signals. These highly accurate signals are tuned to the intrinsic (natural) characteristics of each individual stock (average maximum drawdown and trading frequency).

The intrinsic values (AMD-Average Maximum Drawdown, and trading frequency) are determined by performing an analysis of the entire price history for a given stock, using Monte-Carlo techniques to evaluate hundreds of thousands of possible trades. The objective is to maximize the annualized gain, and the only restriction imposed is that any trade must be held for at least 4 trading days. When this analysis is complete, the natural trading frequency and associated Average Maximum Drawdown are then available. This data is then fed into the optimization process for each of our custom models so that our model values (AMD and trading frequency) can be 'coaxed' to converge to these natural values. This process produces a stock timing model that reflects the natural rhythm of the stock or ETF, and since it is MTI-based, it quickly reacts to the overall temperature of the stock market.

Generalized Candlesticks (the RaDiSH Transform™)

Although our short-term signals (Grail System™) are based on our Market Timing (Temperature) Indicator (MTI), and are thus thermally-based, they do not operate on a sufficiently reactive time scale to be able to predict the daily movement of a single equity like QQQ (since the temperature of the stock market can't change very much in a single day). Instead, we turn to an elegant generalization of Japanese Candlesticks. By applying our proprietary transform (RaDiSH Transform™) we can convert the four daily prices (High, Low, Open, Close) plus volume, into a set of 5 dimensionless and time-invariant numbers. Then, by using this data to train a neural network we can predict the average price that a given stock 'may' exhibit on the next trading day (the sum of the High and Low prices divided by 2). Finally, by looking at the actual Open price of QQQ, together with this estimated average price for the next day, we can calculate the probability that QQQ will Close higher than its Open. This gives us a QQQ day-trading signal that is probably about as accurate as is theoretically possible. A sample Prediction Table report can be seen here.

ETF Decomposition of Mutual Funds

Our Mutual Fund Timing Indicator (MFTI) was developed using our Stock Market Timing Indicator (MTI) as a basis, and this works very well to identify those protracted periods when mutual funds (as an investment class) are in either a 'buy' or a 'sell' state. However, the task of developing buy/sell/hold signals for individual mutual funds requires a different approach. Simply looking at the recent price history of a fund shows its current performance, but offers little insight as to how the fund will perform over the next month or two. Our solution is to try to determine the current holdings of the mutual fund, and then to use our intermediate-term buy/sell/hold (and short-term buy/sell) signals to calculate a weighted signal for the entire fund.

Our approach is to decompose each mutual fund into a weighted sum of 5 different ETFs (basis vectors) that are chosen from a large set of 175 ETFs. Monte-Carlo methods are then used to determine the 5 'best' ETFs, and their associated weightings, that reproduce the recent price history of the mutual fund most accurately. These decompositions are often uncannily accurate, and correlation coefficients (R**2) of 0.9900 or better are routinely achieved. While these decompositions can never exactly reflect the current holdings of a mutual fund, they nonetheless give us an analytical way of assigning a net Score (and a buy, sell, or hold recommendation) for over 1,100 funds on a daily basis. A sample mutual fund decomposition report can be seen here.

Differential Signals -- Comparing Two Indices

By employing a mathematical device we can utilize our Grail System™ techniques to generate models for new 'signals' that predict the relative performance of one index against another. We actually utilize ETFs for this purpose, and the objective is to predict whether, for example, QQQ (the Nasdaq 100) will outperform (or underperform) the S&P 500 (SPY), the DOW (DIA), or the Russell 2000 (IWM) over the near-term. A '+/-' value for the $NQ-RU signal, for example, would mean that a simultaneous Long of QQQ and a Short of IWM (i.e., a hedged situation) would likely be profitable; a '-/+' signal would suggest a profitable QQQ Short while going Long on IWM. We currently generate a total of 31 differential signals, and a recent Differential Signals report can be seen here.

Schulenberg and Associates, LLC: Thermodynamic Stock, ETF, and Mutual Fund Timing Signals and Portfolios

Key Links