TimeGPTOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for TimeGPT-style time series forecasting model.

Inheritance: ModelOptions → RegressionOptions<T> → TimeSeriesRegressionOptions<T> → TimeGPTOptions<T>

For Beginners

TimeGPT brings GPT-like capabilities to time series:

The Key Insight: Just as GPT was trained on internet-scale text data to become a general-purpose language model, TimeGPT is trained on millions of diverse time series to become a general-purpose forecasting model.

Core Features:

  1. Large-scale Pre-training: Trained on millions of time series
  2. Zero-shot Forecasting: No training needed for new data
  3. Uncertainty Quantification: Provides prediction intervals
  4. Multi-horizon: Forecasts at any horizon

Architecture:

  • Positional encoding for temporal information
  • Multi-head self-attention for pattern recognition
  • Large transformer backbone
  • Conformal prediction for uncertainty

Advantages:

  • Works out-of-the-box on new time series
  • No hyperparameter tuning required
  • Handles various frequencies and domains
  • Production-ready forecasting API style

How It Works

TimeGPT represents a GPT-style architecture adapted for time series forecasting, featuring large-scale pre-training on diverse time series data with zero-shot and few-shot forecasting capabilities.

Reference: Garza et al., “TimeGPT-1”, 2023. https://arxiv.org/abs/2310.03589

Constructors

Constructor Summary
TimeGPTOptions() Initializes a new instance of the TimeGPTOptions class with default values.
TimeGPTOptions(TimeGPTOptions<T> other) Initializes a new instance by copying from another instance.

Properties

Property Summary
bool UseConformalPrediction { get; set; } Gets or sets whether to use conformal prediction for uncertainty quantification.
double ConfidenceLevel { get; set; } Gets or sets the confidence level for prediction intervals.
double DropoutRate { get; set; } Gets or sets the dropout rate for regularization.
double FineTuningLearningRate { get; set; } Gets or sets the learning rate for fine-tuning.
int ContextLength { get; set; } Gets or sets the context length (input sequence length).
int FineTuningSteps { get; set; } Gets or sets the number of fine-tuning steps for domain adaptation.
int ForecastHorizon { get; set; } Gets or sets the forecast horizon (prediction length).
int HiddenDimension { get; set; } Gets or sets the hidden dimension size.
int NumHeads { get; set; } Gets or sets the number of attention heads.
int NumLayers { get; set; } Gets or sets the number of transformer layers.