Abstract

It is a well-known fact in finance that classical mean-variance optimization often leads to highly concentrated portfolios. Giving equal weights to all portfolio assets will instead allow for maximum nominal diversification. More sophisticated ways of nominal diversification are the maximum diversification approach proposed by Choueifaty and Coignard (2008) or the equal weighting of total risk contributions known as "risk parity". Instead of looking for nominal diversification, investors may prefer a diversification of the risk factors that drive portfolio returns. In recent papers, risk factors have been modelled by principal components following Partovi and Caputo (2004). Meucci et al. (2013) show that principal components may not be the best way to model risk factors and propose "minimum torsion bets" instead. The present paper discusses different ways of managing diversification and backtests these strategies in a multi-asset portfolio.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call