FalsePositiveRateMetric<T>
Models & Types · AiDotNet.Evaluation.Metrics.Classification
Computes False Positive Rate (FPR): proportion of actual negatives incorrectly predicted as positive.
Implements: IClassificationMetric<T>
For Beginners
FPR answers: “Of all the actual negatives, how many did I incorrectly flag as positive?”
- FPR = 0: Perfect - no false alarms
- FPR = 0.1: 10% of actual negatives are incorrectly flagged as positive
- FPR = 1: All negatives are incorrectly classified as positive
Critical in spam detection (low FPR = fewer legitimate emails marked as spam) and medical screening (low FPR = fewer healthy people incorrectly told they’re sick).
How It Works
FPR = FP / (FP + TN) = 1 - Specificity
Constructors
| Constructor | Summary |
|---|---|
FalsePositiveRateMetric() |
|
FalsePositiveRateMetric(T positiveLabel) |
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) |