Factor investing for the ‘information age’
Date:
18 December 2020
Time: 10:00am - 11:00am
Venue: Zoom Session
Factor investing for the ‘information age’
Factor investing for the 'information age'
Sanne de Boer
Director of Quantitative Equity Research, Voya Investment Management
About the Speaker
Sanne de Boer is director of Quantitative Equity Research at Voya Investment Management responsible for overseeing the firm’s quantitative equity research agenda. Prior to joining the firm, he was a senior research analyst for quantitative strategies for Invesco. Previously, he was a research analyst for global quantitative equities at QS Investors as well as ING Investment Management, Voya’s predecessor firm. Sanne’s research has been published in the Journal of Asset Management, the Journal of Index Investing, and the Journal of Investing. He received a Ph.D. in Operations Research from the Massachusetts Institute of Technology and an M.S. in Mathematics and an M.A. in Econometrics cum laude from the Vrije Universiteit Amsterdam. He holds the Chartered Financial Analyst designation.
Factor investing for the 'information age'
Factors are characteristics of stocks that help explain volatility and dispersion in their returns. Exposure to certain factors has been found to historically have delivered a return premium over the market. “Factor investing” systematically targets stocks with desirable factor exposures, seeking to earn these expected long-term return premiums. In this talk, I will review how factor investing is grounded in fundamental and technical analysis and how it may be implemented in practice. I'll discuss how recent developments such as the increasing availability of alternative (i.e., non-financial) "big" data and advances in Machine Intelligence and Natural Language Processing will not fundamentally change the philosophy behind factor investing, but rather further its scope. In addition, I will touch upon portfolio construction for active equity strategies. Mean-Variance Optimization, invented over 50 years ago, is still in wide use due to its flexibility but suffers from a lack of robustness. I will cover a range of extensions and alternatives to MVO that address this issue, borrowing techniques from Machine Learning to remain relevant.