MASESeasonalMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.TimeSeries

Computes Seasonal MASE: Mean Absolute Scaled Error with explicit seasonal comparison.

Implements: ITimeSeriesMetric<T>

For Beginners

This is MASE specifically designed for seasonal data:

  • Compares your model to a naive seasonal forecast (same period last year/month/week)
  • MASE < 1: Model beats seasonal baseline
  • Seasonal period could be 7 (daily with weekly pattern), 12 (monthly with yearly pattern), etc.

Essential for evaluating retail, energy, or any data with seasonal patterns.

How It Works

Seasonal MASE = MAE / MAE_seasonal_naive where seasonal naive predicts y[t-m] (m = seasonal period)

Constructors

Constructor Summary
MASESeasonalMetric(int defaultSeasonalPeriod) Initializes the Seasonal MASE metric.

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
T Compute(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals, int? seasonalPeriod)