BayesianStructuralTimeSeriesOptions<T>
Options & Configuration · AiDotNet.Models.Options
Configuration options for Bayesian Structural Time Series models.
Inheritance: ModelOptions → RegressionOptions<T> → TimeSeriesRegressionOptions<T> → BayesianStructuralTimeSeriesOptions<T>
For Beginners
A time series is simply data collected over time (like daily temperatures, monthly sales, or yearly population). Bayesian Structural Time Series is a powerful way to analyze this kind of data by breaking it down into different parts: the overall direction (trend), repeating patterns (seasonality), and the influence of other factors (regression). The “Bayesian” part means it can express uncertainty about its predictions and incorporate what you already know about the data. Think of it like weather forecasting that not only predicts tomorrow’s temperature but also tells you how confident it is in that prediction.
How It Works
Bayesian Structural Time Series (BSTS) models are flexible time series models that decompose a time series into trend, seasonal, and regression components. They use Bayesian methods to estimate model parameters and can handle missing data, incorporate prior knowledge, and provide uncertainty estimates.
Constructors
| Constructor | Summary |
|---|---|
BayesianStructuralTimeSeriesOptions() |
Properties
| Property | Summary |
|---|---|
List<int> SeasonalPeriods { get; set; } |
Gets or sets the list of seasonal periods to model in the time series. |
MatrixDecompositionType RegressionDecompositionType { get; set; } |
Gets or sets the matrix decomposition method used for regression calculations. |
bool IncludeRegression { get; set; } |
Gets or sets whether to include regression components in the model. |
bool PerformBackwardSmoothing { get; set; } |
Gets or sets whether to perform backward smoothing after forward filtering. |
bool UseAutomaticPriors { get; set; } |
Gets or sets whether to automatically determine prior distributions. |
double ConvergenceTolerance { get; set; } |
Gets or sets the convergence tolerance for parameter estimation. |
double InitialLevelValue { get; set; } |
Gets or sets the initial value for the level component of the time series. |
double InitialObservationVariance { get; set; } |
Gets or sets the initial variance of the observation noise. |
double InitialTrendValue { get; set; } |
Gets or sets the initial value for the trend component of the time series. |
double LevelSmoothingPrior { get; set; } |
Gets or sets the prior for the level component’s smoothing parameter. |
double RidgeParameter { get; set; } |
Gets or sets the ridge parameter for regression regularization. |
double SeasonalSmoothingPrior { get; set; } |
Gets or sets the prior for the seasonal component’s smoothing parameter. |
double TrendSmoothingPrior { get; set; } |
Gets or sets the prior for the trend component’s smoothing parameter. |
int MaxIterations { get; set; } |
Gets or sets the maximum number of iterations for parameter estimation. |