Patent · US Active

Probabilistic forecasting with nonparametric quantile functions

US11531917B1 · kind B1 · utility

1Cited by

3References

20Claims

0Family size

Assignee

AMAZON TECHNOLOGIES, INC. · US

Inventors

Jan Gasthaus · Munich, DE
Konstantinos Benidis · Berlin, DE
Yuyang Wang · Shantou, CN
David Salinas · Berlin, DE
Valentin Flunkert · Berlin, DE

Key dates

Filing date	Sep 28, 2018
Grant date	Dec 20, 2022
Priority date	—
Expiry date	Feb 10, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/08
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques are described for a time series probabilistic forecasting framework that combines recurrent neural networks (RNNs) with a flexible, nonparametric representation of the output distribution. The representation is based on the nonparametric quantile function (instead of, for example, a parametric density function) and is trained by minimizing a continuous ranked probability score (CRPS) derived from the quantile function. Unlike methods based on parametric probability density functions and maximum likelihood estimation, the techniques described herein can flexibly adapt to different output distributions without manual intervention. Furthermore, the nonparametric nature of the quantile function provides a significant boost in the approach's robustness, making it more readily applicable to a wide variety of time series datasets.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.