Great Northern Capital equity portfolios utilize proprietary quantitative modeling to provide a
systematic, repeatable, dynamic process that forecasts expectations for the near-term while adjusting
for the current investment environment. The Great Northern investment process utilizes multiple factor
quantitative models that are grounded in a bottom-up fundamental approach. The logic-based (non-
black box) models utilize the most recent publicly disclosed financial and market information. The Great
Northern Small Cap, SMID Cap, and AlphaMax long/short product each provide an actively
managed, diversified portfolio of 50 stocks generated from a stock selection process that uses
proprietary algorithms and statistical forecasting techniques systematically adjusted for the current
market environment.
The models are dynamic, utilizing a number of proprietary analytical components to generate the stocks
ultimately selected for each portfolio. Approximately 60 factors are included in the models to increase
diversification of information and manage portfolio risk. This reflects the theory that more information
leads to better stock picking forecasts.
A critical consideration in the Great Northern investment process is that certain factors perform
statistically better or worse in different market environments. The changing market environment is
measured through a series of market indicators that are weighted each month. Not every Market
Environment Indicator gives a positive or negative signal each month. When a signal is statistically
significant, the indicator is included and the level of significance is incorporated.
The models then analyze how the Market Environment impacts the effectiveness of each factor.
Proprietary algorithms and statistical analyses techniques are employed to systematically adjust the
forecasted effectiveness of each factor on a monthly basis.
The Great Northern investment process then incorporates a statistical methodology to determine model
weights, which are used to generate the 50 stocks ultimately selected for each portfolio.
|
