Statistically robust for more reliable alpha
In the search for risk-free alpha, quantitatively driven funds need a statistically robust model that minimises the overlap between risk and alpha and accounts for the heteroskedasticity in security returns.
EMA’s Alpha Toolbox corrects for this “contemporaneous/simultaneous estimation bias” to allow for use of full-information maximum likelihood estimation techniques for risk-adjusted testing of valuation/trading models.
This improves the probability that a historically observed alpha will deliver risk adjusted outperformance in future.
The FASTVaR models of daily updated forecast volatility and correlation are the theoretically correct match to a set of expected returns improving the prospects for the construction of efficient portfolios.
In operation, EMA’s Excerpt risk analysis system can be delivered as an API to facilitate the integration of its advanced analytics into any front or middle office platform.