Michael J. Valletutti, founder of MarketModel Advisors, has quickly become a popular, largely followed investment commentator, since starting his sharing of ideas on Twitter in 2012. With his proprietary market timing model, which provides a probabilistic prediction of the direction of the stock market, the firm has evolved from providing investment research products for a wide range of clients - DayTraders, Professionals and Institutional Managed Accounts - to managing a commodity pool for Accredited Investors.

Following the 1987 market crash he began developing his futures trading market model while studying statistics & probabilities, time series analysis, probability modeling, and statistical experiments at Georgia Institute of Technologies.“My passion was the stock market, having witnessed the ‘87 crash as a Sophomore at Georgia Institute of Technologies,” Michael comments, “Merging together the circumstances and opportunities following the crash and my passion for the market, I came up with some economic and technical rules that performed well when applied to historical data. And then I worked for over 15 years refining the model.”

After sharing live model signals through 2015 via an email subscription service, with the successful outcome of these trades, as well as hypothetical backtested results, the firm has registered as a CPO with the National Futures Association (NFA) and is soliciting funds from accredited investors in 2016.

Model Background

The goal of the model is to achieve highest risk-adjusted returns.

The data collected and analysis created
by the model hasn’t changed since inception.

Since 1990, his model has input nightly data from over 50 sources -- including price, volume, interest rates, options, and causal data -- to predict the direction of the SP500 with probability. His unique model measures macro and technical intermarket relationships that provide analysis around both trend and counter-trend moves.
The fundamental thesis behind the model hasn't changed since early 1990s. However, the application of the model's signal has improved to include risk management techniques. The model produces not only a prediction of direction of SP500, but also a probability strength of signal. Based on this conviction level for the trade, the fund applies risk management techniques in making the investment, allowing for scaling in and out of positions.

Model Theory

The fundamental theory is that macroeconomic conditions lead stock market prices. If true, producing accurate, forward-looking economic forecasts (i.e. ATL Fed GDPNow) could provide clues to the future direction of the major stock indices (i.e. SP500).  Often times, stock market prices are controlled by sentiment - greed and fear - which can lead to disconnects between price's "fair value". The model wants to buy the market when price is a discount to fair value, and short the market when price is a premium to fair value.

The model isn't a crystal ball. Trade signals are based on Probabilities and Statistical methods, producing different trades with differing probability of success. Overall, model is right 2 out of 3 trades.

More recently, research has been focused on limiting maximum exposure to the stock market.  Today's markets are faster than ever, and high velocity of price movements is normal.  Typical equity allocation strategies are too heavily invested in equities (i.e. 80% long).  Worse yet, most hedge fund strategies use leverage in an attempt to outperform the index.  These strategies will suffer with the increased velocity of price.

The model is not a HFT or intraday scalping algorithm, only changing the position about 2-3x a month, on average. The model is a pure directional bet on whether the SP500 will rise or fall, which during bull or bear markets, is able to profit from not only the major trend but also sell into the minor counter-trends. The result is a system designed to beat the SP index by profiting when the market loses during pullbacks.


Underweight SPX Trading Fund
MAX 1x Long/Short
averages 42% SP position size
NO Leverage
additional benefit of profitable short trades
Live Tested Returns

Testing Strategy
(10+ years)

The model has been running daily since 2006, generating daily signals that resulted in long or short positions in the SP500.  The long-term win rate of 67% has been maintained over the past 10 years of live testing, without any changes to the original model theory of the early 1990s.

Prior to fund inception, the daily model trades were delivered via professional subscription since Jun 2013. Those proprietary results were consistent with backtested results. 

In 2014, an updated scaling strategy - building position sizes between 15% to 100% - resulted in larger realized profits as well as the win rate, combined with taking less risk during the rare signals (MAX).

Based on the improved results of the proprietary testing, along with the multiple years of monitoring the outcomes of many years of model trades in real-time, Mr. Valletutti started the investment fund in December 2015, and then pooled client funds in February 2016.

Market Neutral, Non-correlated Model

A key measure for alternative investments is correlation. Asset allocation models prefer non-correlated investments to their equity allocation, and the model performs independently with the SPX, up and down markets.  The model's correlation factor of 0.07 demonstrates an investment strategy that is almost completely hedged.
The test results were put together by a Risk Officer from a separate hedge fund, measuring live testing between 2006-2012 using MAX 300% strategy.

Hurdle = 3%
RF = 2.50%
Expected Market Return = 7%
Market Return = 0.946%

The following table represents the testing results of the model's real-time trading performance, including annualized rate-of-returns.  The Sharpe ratio characterizes how well the return of an asset compensates the investor for the risk taken. The Sortino Ratio, a modification of the Sharpe, but penalizes only those returns falling below a user-specified minimum rate of return. Together, they demonstrate a favorable level of risk for the returns achieved.
Compound Annual ROR = 28.96%
Daily St Deviation = 0.016
Annual St Deviation = 0.251
Excess Return = 26.19%
Daily Variance = 0.0002
Correlation = 0.074
R Squared = 0.006
Beta = 0.084
Actual Alpha = 26.32%
Adjusted Alpha = 25.81%
Sorting Ratio = 1.8603
Sharpe Ratio =  1.043


Michael J. Valletutti Biography



Georgia Institute of Technology
BIE: Bachelors of Engineering - Industrial
MSIE: Masters of Science - Probability & Statistics
Develops initial macro model


Commodity Trading Advisor (CTA) – NFA Registered
Collects nightly market data for input into model
Tracks and refines model with virtual money


Chairman and CEO, Applied Global Technologies (AGT)
Co-founder, Video Managed Services and Technology
$25M Small Business, 100+ employees
Private Equity Event


Founder, MarketModel Advisors, LLC
Twitter @marketmodel
Shared model trades via email subscription service


Commodity Pool Operator (CPO) - NFA Firm Registered
Underweight SPX Trading Fund, LP

Information about Modeling

What is a model?

Backward Testing

A simple example of a market model is comparing today's price to the historical average of price over, for example, the 50 past days. The rule would be to BUY when today's price is above the past average, and SELL if below. This rule could be easily backtested and other rules could be applied to produce win/loss ratio and profit/loss delta. Other rules could be applied and tested, but not so many that the rules only work for the test data. Known as curve-fitting, too many of today’s rules are created to fit just one set of past data, which will not work for new data. In simple terms, the rules were so stringent that they could only work once.

Forward Testing

The next method for a model is to forward test, which measures the results against future data. Since 2006, Michael has been applying the model in real-time to the daily trade of the SP500. In fact, between 2006-2010, he posted the daily model signals on the web and also paper-traded the positions. The results were consistent with the historical testing, and produced very good returns in both bull and bear markets. In fact, the model's best year was during the 2008 financial crisis.

Testing with Real Money

By 2012, Michael’s confidence in his own MarketModel led him to establish a futures account and commit to trading the model signals, following the direction and probability signals of the model. Michael's trading diary moved to social media via Twitter @marketmodel, where the nightly model signals were posted, along with trading results.

The model uses SP500 futures instead of the SPX cash because of the use of leverage provided by futures. Use of leverage is typically associated with high risk, however in our case, we are simply choosing to not to tie up $1M is cash buying and selling shares of the SPX. Leverage allows for the scaling from underweight SP500 to up to 1x leveraged (100% long or short).

The model's use of leverage allows for scaling into very large account balances. For example, a $1B account could invest alongside the model within the SP futures market easily within the avg volume and open interest of today's market.  The investment decisions are almost entirely systematic, based on the model's signals.


Michael J. Valletutti, CTA

NFA ID 0267975

MarketModel Advisors LLC, CPO

NFA ID 0491458

Merritt Square Financial Center
775 E Merritt Island Causeway
Suite 120
Merritt Island, FL 32952