Low-volatility equity
PortfolioAdvanced
A low-volatility portfolio holds the stocks with the smallest historical return volatility and avoids the most volatile names. It is related to betting against beta but ranks volatility, not beta, and it is often run long-only. The research claim is that the low-risk group has not delivered the lower return that a simple risk model would suggest. Implementation is a universe rule plus a rebalance.
Not investment advice. Nothing here is a recommendation to buy or sell anything. Backtests and historical studies are not guarantees, and a rule that worked in one sample can fail in the next. Trading can lose money. Links are for education, not endorsements. Do your own research.
- Rules
- Each month, measure trailing volatility, such as one-year daily standard deviation, and buy the lowest quintile in equal weight or in a minimum-variance mix inside that quintile. Drop names that fail a liquidity screen. Rebalance monthly. Keep it long-only unless the specification includes a short book. Do not add a high-volatility name because a narrative says it is 'quality.'
- Where AI fits
- AI can compute trailing volatility without look-ahead, apply the liquidity screen on the signal date, and compare holdings with a beta sort. It can also run the same rule inside sectors so a low-vol portfolio is not secretly a sector bet. The volatility window should be chosen before the test evaluation.
- Markets
- Liquid stocks. Using it on a handful of mega-caps removes the cross-section the strategy needs.
- Timeframes
- Monthly rebalance. The volatility window is typically months to a year.
- Risks
- Low-volatility stocks can be interest-rate sensitive and can fall together. The group can lag badly in a speculative rally and then look broken at the worst time to abandon it. Volatility estimates jump after a shock. Long-only low vol is still equity market risk. Historical studies are not forecasts.