Standard Deviation
Standard deviation measures how widely a set of returns spreads around its average, serving as the most common statistical proxy for volatility and risk.
Standard deviation is a statistic that quantifies dispersion: how far individual observations typically fall from the mean. You compute it by taking each return's deviation from the average return, squaring those deviations, averaging the squares (the variance), and taking the square root to return to the original units. A small standard deviation means returns cluster tightly around the average; a large one means they swing widely in both directions.
In finance, standard deviation of returns is the standard measure of volatility and one of the oldest definitions of risk. It underpins the Sharpe ratio, which divides excess return by standard deviation, and it is a building block of modern portfolio theory and the efficient frontier. Annualized volatility, the figure usually quoted, is the periodic standard deviation scaled up by the square root of the number of periods per year.
Standard deviation has well-known limitations as a risk measure. It treats upside and downside deviation identically, even though investors fear losses more than they dislike gains, which motivates downside-focused alternatives like the Sortino ratio and semi-deviation. It also assumes a roughly stable, bell-shaped distribution and can badly understate the chance of extreme moves in markets that exhibit fat tails. It is best understood as a useful first approximation of risk, not the whole picture.
hedgewing.ai uses volatility estimates throughout its pipeline, both as one of the 45 engineered features that feed its deep-learning ensemble and as a component of the risk analytics it reports. Standard deviation also calibrates the platform's confidence intervals, helping translate the ensemble's point forecasts into probabilistic ranges rather than false-precision single numbers.
Related terms
Volatility · Sharpe Ratio · Correlation · Value at Risk (VaR)
Back to the hedgewing.ai glossary · See AI stock forecasts