Using Upside-to-Downside Deviation in Portfolio Selection

Summary

The post asks whether the ratio of upside deviation to downside deviation can guide portfolio weights. Its author informally calls the ratio “acceleration” and imagines using it to size a momentum strategy, on the intuition that upside variation represents reward while downside variation represents risk. The question is exploratory: it does not define a calculation or present a tested allocation rule.

The response says the ratio has been used as a portfolio-selection criterion and points to empirical studies comparing alternative selection and risk-reward objectives. It reports that, in those studies, reducing downside mattered more than increasing upside. This offers a practical caution against assuming that a high upside-to-downside ratio will improve a portfolio simply because upside is desirable. The excerpt gives no study design, assets, performance figures, or implementation details, so it cannot establish how the criterion performs across markets or whether the result applies to momentum weighting. Readers would need to consult the cited research and evaluate the measure against their own portfolio constraints and risk objectives.

Key ideas

• Upside-to-downside deviation can be considered as a portfolio-selection criterion.
• The post proposes, but does not test, using the ratio to weight a momentum strategy.
• The cited empirical work reports that reducing downside was more important than increasing upside.
• The excerpt does not specify a formula, allocation procedure, or evidence details.

Tags

# The ratio of upside deviation to downside deviation in portfolio weighting


# The ratio of upside deviation to downside deviation in portfolio weighting












I've been calling this ratio "acceleration" in my head, so I'll do the same in this post. The question is, is this relationship used anywhere and if so, how? My thought process is as follows.

Risk is typically quantified through standard deviation. But how good of a proxy for risk is SD really? Upside deviation is not risk, it's the definition of reward!

So "acceleration" might quantify upside variance per unit of downside variance. I can imagine a momentum strategy using an "acceleration-weighted" allocation scheme. Like riding a rising wave.

This could also be some obscure Greek that I'm not aware of, or have a completely different use. Just wondering. Thanks.

## Answer by Enrico Schumann (score 1)

https://quant.stackexchange.com/a/54089

We have used it as a criterion for portfolio selection, for example in An Empirical Analysis of Alternative Portfolio Selection Criteria and Risk-Reward Optimisation for Long-Run Investors: An Empirical Analysis. What we found there, however, is that reducing the downside was more important than increasing the upside.

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.