Featured Image

The Integration of the Alpha Alignment Factor and Earnings Forecasting Models in Producing More Efficient Markowitz Frontiers

Companies and Earnings   |   Fixed Income   |   Performance and Risk

By FactSet Insight  |  January 13, 2015

Bijan Beheshti, manager of portfolio and quantitative analytics at FactSet's San Francisco office, was recently published in The Journal of Investing. His paper, The Integration of the Alpha Alignment Factor and Earnings Forecasting Models in Producing More Efficient Markowitz Frontiers, can be found in the Winter 2014 issue or online at IIJournals.com.

Abstract

In this study, we explore problems that arise during the portfolio optimization process that ultimately result in disappointing performance. This is a common problem in quantitative investment management which leaves investors wondering why their strong alpha signals did not transform into superior investment results once they transitioned from research to portfolio construction. We assert that the use of strong alpha signals, statistically based risk models, and a robust optimization engine that allows for the correction of alignment problems alleviate the traditional pitfalls that cause optimized portfolios to be less than optimal. We run hundreds of scenarios utilizing CTEF, an earnings forecasting model developed by John Guerard of McKinley Capital Management, to derive expected return estimates. Further, we use Axioma's World Wide risk models and optimization engine which enables us to apply its proprietary Alpha Alignment Factor during the optimization process. Finally, we construct our portfolios, alpha signals, and analytics using FactSet's Portfolio Simulation and Portfolio Analysis applications as well as the FactSet Fundamentals and FactSet Estimates databases. 

iijournal.jpg

Download the full article.

Comments

Info

We use cookies to personalize content and ads and to analyze our traffic.

We also share information about your use of our site with our advertising and analytics partners. See details.