Optimal stop-loss rules in markets with long-range dependence

Abstract

Stop-loss is a common risk management tool for limiting risks and improving trading strategy performance. The effectiveness of stop-loss depends critically on asset price characteristics. This study is the first to analyze stop-loss strategy incorporating long-range dependence of asset prices through a fractional Brownian motion-based market model. It is shown that stop-loss strategy yields a positive return premium over the buy-and-hold return when asset price exhibits long-range dependence. The efficacy of stop-loss strategies and the determining criterions are investigated through both theoretical analysis and simulation studies. The performance of a stop-loss rule depends on the Hurst parameter, mean and volatility of the asset returns. The optimal stop-loss threshold model in a chosen strategy class is fitted by polynomial regression. Empirical analysis demonstrates that the class-specific optimal rules outperform stop-loss rules under alternative asset return-generating models.

Keywords:

• Stop-loss
• Risk management
• Investments
• Fractional Brownian motion
• Fractal markets

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 The stop-loss policy depends on verifiable market conditions and specification of asset price dynamics, which are fully specified with respect to a chosen market model.