PrecisionMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.Classification

Computes precision (positive predictive value): the proportion of positive predictions that are correct.

Implements: IClassificationMetric<T>

For Beginners

Precision answers: “When the model predicts positive, how often is it correct?” High precision means few false positives (false alarms). A spam filter with 99% precision means only 1% of emails it flags as spam are actually legitimate.

How It Works

Precision = TP / (TP + FP) = True Positives / Predicted Positives

When to prioritize precision:

  • When false positives are costly (blocking legitimate transactions, accusing innocent people)
  • When you need high confidence in positive predictions

Multi-class: For multi-class problems, use averaging (micro, macro, weighted) to combine per-class precision values.

Constructors

Constructor Summary
PrecisionMetric(AveragingMethod averaging) Initializes a new precision metric with default positive label (1).
PrecisionMetric(T positiveLabel, AveragingMethod averaging) Initializes a new precision metric with an explicit positive label.

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)