Systematic Strategy Improvements Through Risk Models and Execution

Summary

The document raises several ways to strengthen systematic strategies: estimate portfolio risk using correlations instead of relying only on equal weighting or inverse-volatility weighting, model transaction costs, and add constraints to mean-variance optimization. These are presented as candidate improvements rather than developed procedures.

The answer highlights execution as another important component. Portfolio changes can incur implementation shortfall, and execution methods should account for that cost. For a market-neutral portfolio, passive orders may fill at different speeds when the market trends, temporarily creating unwanted directional exposure. The discussion points to optimal execution research as relevant background, but includes no comparison, data, or quantified results. The suggestions are broad and need to be evaluated against a strategy’s assets, trading horizon, liquidity, and implementation needs.

Key ideas

• Correlation-based risk estimates can inform portfolio weights beyond equal or inverse-volatility schemes.
• Transaction costs and constraints are practical additions to systematic strategy design.
• Execution choices affect implementation shortfall when changing portfolio positions.
• Uneven passive fills during a market trend can temporarily break a portfolio’s market neutrality.

Tags

# Methods to improve systematic strategies


# Methods to improve systematic strategies












Soliciting advice on ways to improve systematic strategies. Some things that I can think of off the top of my head:

- Using a risk model (correlations) instead of 1/n or 1/vol weighting

- Including a transaction cost model

- Adding constraints to MVO optimization

Any others that people can think of?

## Answer by numerairX (score 6)

https://quant.stackexchange.com/a/41946

Order execution optimization: how to execute changes to your portfolio without suffering (too much) from implementation shortfall. Work of Almgren and Chris set a modern foundation of this space, and on top of that work of Jim Gatheral for closed form solution. In addition, consider if you're executing an order for market neutral portfolio but market is trending one way, if you only submit passive orders, one way will be filled faster than the other direction which leads to breach of neutral. I learned this idea from my professors' work which also offer a solution to this problem, check Optimal Microstructure Trading with a Long-Term Utility Function!

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

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