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:
- Large-scale Pre-training: Trained on millions of time series
- Zero-shot Forecasting: No training needed for new data
- Uncertainty Quantification: Provides prediction intervals
- 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. |