RollingVolatilityTransformer<T>

Models & Types · AiDotNet.Preprocessing.TimeSeries

Computes rolling volatility and return-based features for financial time series.

Inheritance: TimeSeriesTransformerBase<T> → RollingVolatilityTransformer<T>

For Beginners

Volatility measures how much a price moves up and down over time.

High volatility means:

  • Prices change a lot day-to-day
  • Higher risk but also higher potential returns
  • Common during market uncertainty

Low volatility means:

  • Prices are relatively stable
  • Lower risk but also lower potential returns
  • Common in stable market conditions

This transformer creates features like:

  • Simple returns: (Today’s price - Yesterday’s price) / Yesterday’s price
  • Log returns: ln(Today’s price / Yesterday’s price) - preferred for statistical analysis
  • Realized volatility: Standard deviation of returns over a window
  • Momentum: How much price has changed over a period

How It Works

This transformer calculates volatility measures commonly used in quantitative finance, including realized volatility, Parkinson, and Garman-Klass estimators.

Constructors

Constructor Summary
RollingVolatilityTransformer(TimeSeriesFeatureOptions options) Creates a new rolling volatility transformer with the specified options.

Properties

Property Summary
bool SupportsInverseTransform { get; }