TweedieLossMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.Regression

Computes Tweedie Deviance Loss for regression with power parameter.

Implements: IRegressionMetric<T>

For Beginners

Tweedie loss is flexible for different data types:

  • Power = 0: Normal distribution (like MSE)
  • Power = 1: Poisson distribution (count data)
  • Power = 2: Gamma distribution (positive continuous)
  • Power = 3: Inverse Gaussian distribution
  • 1 < Power < 2: Compound Poisson-Gamma (insurance claims)

How It Works

When to use:

  • Insurance claim prediction (zeros and positives)
  • Sales forecasting with many zeros
  • Any data with mixed zero and positive values

Constructors

Constructor Summary
TweedieLossMetric(double power)

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)