About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
INFORMS 2021
Talk
Alternate Forecast: a GMM based representation of forecast and prediction interval
Abstract
Prediction interval represents uncertainty associated with a forecast. The uncertainty has two origins, parameter estimation uncertainty, and parameter estimation bias. The former is generally attributed to the data size used to estimate the model parameters, while the latter capture bias in the training. The unimodal distribution assumption of the prediction interval is key to devising computationally efficient prediction interval estimation. But, this assumption often fails in a non-linear forecasting setup. In this work, we represent an efficient Gaussian Mixture Model-based prediction interval representation, capable of addressing this issue. Each mixture component represents an alternate forecast with associated uncertainty.