predict.conformalRegressorByHorizon

This function generates prediction intervals that account for increasing
uncertainty at longer forecast horizons. Each horizon h uses its own
calibrated nonconformity score distribution, resulting in trumpet-shaped
prediction intervals.

Conformal time series forecasting using the caret infrastructure.
It provides access to state-of-the-art machine learning models for forecasting
applications. The hyperparameter of each model is selected based on time
series cross-validation, and forecasting is done recursively.

Resul Akay

caretForecast

Conformal Time Series Forecasting Using State of Art Machine
Learning Algorithms

predict.conformalRegressorByHorizon function

<dl><dt>object</dt>
<dd>A conformalRegressorByHorizon object</dd>
<dt>y_hat</dt>
<dd>Predicted values (one per horizon)</dd>
<dt>confidence</dt>
<dd>Confidence level(s) between 0 and 1 (e.g., 0.95 for 95 percent)</dd>
<dt>y_min</dt>
<dd>The minimum value to include in prediction intervals</dd>
<dt>y_max</dt>
<dd>The maximum value to include in prediction intervals</dd>
<dt>...</dt>
<dd>Ignored</dd></dl>

Arguments

Author

Predict intervals from a horizon-specific conformal regressor — predict.conformalRegressorByHorizon

<dl>

<dt>object</dt>
<dd>A conformalRegressorByHorizon object</dd>


<dt>y_hat</dt>
<dd>Predicted values (one per horizon)</dd>


<dt>confidence</dt>
<dd>Confidence level(s) between 0 and 1 (e.g., 0.95 for 95 percent)</dd>


<dt>y_min</dt>
<dd>The minimum value to include in prediction intervals</dd>


<dt>y_max</dt>
<dd>The maximum value to include in prediction intervals</dd>


<dt>...</dt>
<dd>Ignored</dd>

</dl>

predict.conformalRegressorByHorizon: Predict intervals from a horizon-specific conformal regressor

Description

Usage

Value

Arguments

Author