Scientific Beta

This paper introduces the methodology and conceptual groundings of the Scientific Beta Maximum Decorrelation indices. The Maximum Decorrelation strategy aims to minimise the volatility of a portfolio of stocks under the assumption that individual volatilities are identical, thus only exploiting the correlation structure. This approach is an application to equity portfolio construction of the diversification measure suggested by Christoffersen et al. (2010). Highlighting the specific risks of the Maximum Decorrelation approach, we explain how this strategy mitigates parameter estimation risk by avoiding expected returns estimation, avoiding volatility estimation, and using a robust correlation estimation method.

This paper introduces the methodology and conceptual groundings of the Scientific Beta Maximum Decorrelation indices.

The Maximum Decorrelation strategy aims to minimise the volatility of a portfolio of stocks under the assumption that individual volatilities are identical, thus only exploiting the correlation structure. This approach is an application to equity portfolio construction of the diversification measure suggested by Christoffersen et al. (2010). Highlighting the specific risks of the Maximum Decorrelation approach, we explain how this strategy mitigates parameter estimation risk by avoiding expected returns estimation, avoiding volatility estimation, and using a robust correlation estimation method. Overall, our findings suggest that the Maximum Decorrelation strategy provides potential for outperformance through better diversification across stocks, while its risk exposures can be modified using a suitably designed risk control framework.