Practical Applications of Dynamic Allocation or Diversification: A Regime-Based Approach to Multiple Assets

Abstract

Practical Applications Summary In Dynamic Allocation or Diversification: A Regime-Based Approach to Multiple Assets , published in the in the 2017 special multi-asset class issue of The Journal of Portfolio Management , Peter Nystrup, Bo William Hansen, Henrik Olejasz Larsen, Henrik Madsen , and Erik Lindstrom investigate a dynamic asset-allocation strategy based on increasing exposure to risky assets during periods of low volatility and decreasing exposure to risky assets during periods of high volatility. The signal to change allocation comes from a regime-switching model based on the MSCI World Index. The strategy uses a “hidden Markov model” to detect changes from a regime of high volatility to low volatility and vice versa. The authors test their model-driven dynamic strategy over the period from 1997 through 2015. They conclude that their model-driven dynamic strategy outperforms a benchmark strategy of 60% equities and 40% fixed-income. They further conclude that the optimal implementation of their strategy is to overly it on the benchmark strategy and to apply the dynamic approach to roughly 80% of the total portfolio. Implementing the strategy on 80% of the total portfolio produces the highest Sharpe ratio.