RelativeAbsoluteErrorMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.Regression

Computes Relative Absolute Error (RAE): sum of absolute errors relative to baseline.

Implements: IRegressionMetric<T>

For Beginners

RAE is the absolute error version of RSE:

  • RAE < 1: Your model is better than the mean baseline
  • RAE = 1: Your model equals the mean baseline
  • More robust to outliers than RSE
  • Commonly used in time series forecasting

How It Works

RAE = Σ|y - ŷ| / Σ|y - ȳ|

Constructors

Constructor Summary
RelativeAbsoluteErrorMetric()

Properties

Property Summary
MetricDirection Direction { get; }
T MaxValue { get; }
T MinValue { get; }
bool RequiresProbabilities { get; }
bool SupportsMultiClass { get; }
string Category { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
MetricWithCI<T> ComputeWithCI(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals, ConfidenceIntervalMethod ciMethod, double confidenceLevel, int bootstrapSamples, int? randomSeed)
T Compute(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals)