Multi-Factor Beta load targeting enhanced by supervised machine learning and tuned by proprietary AI holds long and short positions across a dynamic universe 600 stocks composed of long single stock constituents, short single stock constituents and short tactical ETF’s for beta load optimization across 26 custom factors and 13 industry sectors.

Factor related returns, referred to as “Alpha”, are maximized while exposure to common returns, or the sum of returns from known factors, are constrained within very tight beta limits from slightly negative to slightly positive. Concurrently, 26 custom factors tactically target specific beta loads relative to their corresponding group of stocks and the portfolios primary benchmark, creating two distinct beta values. To enhance overall portfolio performance, these beta values play a critical role in simultaneously managing portfolio volatility in real time and on a forward basis. Unlike traditional strategies, which are backward looking and adjust their beta exposures based on events that have just occurred, we predict volatility and adjust ahead of it. If our models are wrong, the feedback loop helps the AI better understand its environment and quickly adjust. Returns attributable to common factors, such as sector, style, size and volatility, are kept within very tight constraints so the excess returns, or alpha, delivers almost all the gains. Investors should not have to pay performance fees for common returns, there are inexpensive index trackers and themed ETF’s that do just that.

Universe components are selected based on market capitalization, daily trading volume and the stock’s beta relative to its primary industry peer group as well as the stocks beta to the SP 500 and MSCI Total World Index. Each of the 26 factors have variable beta load targets while the overall portfolio is always beta neutral versus the SP500 and/or MSCI Total World Index. This is a key differentiator that enables clients to rest easy at night knowing any type of event, even black swan scale, will not shock the portfolio, on the contrary, it will provide for a very brief opportunity to lock in substantial excess returns.

The algorithm is designed to generate portfolio gains from Specific Returns, or independent of (uncorrelated with) common factors and the specific returns to other assets. This is the alpha. In other words, the specific return is the return coming from model behavior rather than returns common to similar investments styles and strategies. The differentiation between Factor-Related and Specific Returns of common stocks was first introduced in the Journal of Finance (VOL. XXXVII, No. 2, May 1982).



Alpha is maybe the most misrepresented quantity in finance. It is most often cited as the absolute excess returns above a benchmark index, so that if a US large cap benchmark delivered 10% returns in a period, and a large-cap equity mutual fund delivered 12% in the same period, many people would say the manager had delivered 2% of alpha. This is (often egregiously) incorrect. The true definition of alpha is the excess return from a strategy that cannot be explained by the strategy’s sensitivity to an underlying benchmark (or other factors):

The critical component is β, which is a function of the correlation of the strategy with the benchmark, and the strategy’s relative volatility. So a strategy’s beta is high if it is highly correlated with the benchmark, and it has a relatively high volatility. Conversely, the beta is low if it has a low correlation with the benchmark or it has a low relative volatility.

Beta is traditionally determined by regressing the returns to the strategy on the returns to the benchmark because this method also, quite conveniently, also yields the alpha. After all, alpha is simply the intercept term in the linear regression. Of course, there is a random component to alpha, as with all analysis of financial time series, so it helps to know the statistical significance of alpha. This is measured as a standard t-score, which allows us to source a probability value that the strategy’s alpha is statistically significant. This t-score is a direct function of both the number of observations, and the magnitude of alpha, so we can be more confident of alpha being a reflection of skill vs. luck with a longer observation horizon, or if the magnitude of alpha is quite large.

Lastly, some might be concerned with a strategy’s information ratio (IR). Recall that the IR is also measured against a benchmark, and tracks the strategy’s excess returns above the benchmark’s returns per unit of tracking error. It is essentially a relative Sharpe ratio, where the return series used to calculate Sharpe is the daily returns to the strategy minus the daily returns to the benchmark.

Benchmarks:: SP500 & MSCI Total World Index