Skip to content
All library documents

Markowitz Portfolio Management for Moving-Band Statistical Arbitrages

Article arXiv papers · Author: Kasper Johansson et al.
Read the original

Summary

This work considers how to manage a changing portfolio of moving-band statistical arbitrages using ideas from the Markowitz portfolio optimization framework. Rather than treating a single arbitrage in isolation, it describes managing a dynamic basket of these strategies, with portfolio construction as the central problem.

The authors illustrate the method using recent historical data and report that the resulting basket can achieve strong risk-adjusted returns while remaining essentially uncorrelated with the market. The excerpt does not specify how the moving bands are defined, how assets or arbitrages are selected, which optimization constraints are imposed, or what sample period and performance measures are used. The reported outcome therefore provides an illustration rather than enough evidence to establish robustness across market regimes or live trading conditions.

Key ideas

  • The method applies Markowitz-style portfolio management to a dynamic basket of moving-band statistical arbitrages.
  • The approach treats basket management as a portfolio construction problem.
  • A historical-data illustration reports strong risk-adjusted returns.
  • The illustrated basket is described as essentially uncorrelated with the market.
  • The excerpt omits implementation details and evidence needed to assess out-of-sample robustness.

Tags

Mean reversionPortfolio constructionRisk managementBacktesting
Full text
# A Markowitz Approach to Managing a Dynamic Basket of Moving-Band Statistical Arbitrages


# A Markowitz Approach to Managing a Dynamic Basket of Moving-Band Statistical Arbitrages









We consider the problem of managing a portfolio of moving-band statistical arbitrages (MBSAs), inspired by the Markowitz optimization framework. We show how to manage a dynamic basket of MBSAs, and illustrate the method on recent historical data, showing that it can perform very well in terms of risk-adjusted return, essentially uncorrelated with the market.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.