公开(公告)号：US11281969B1

公开(公告)日：2022-03-22

申请号：US16116631

申请日：2018-08-29

Applicant: Amazon Technologies, Inc.

Inventor： Syama Rangapuram ,  Jan Alexander Gasthaus ,  Tim Januschowski ,  Matthias Seeger ,  Lorenzo Stella

IPC: G06N3/08 ,  G06N7/00 ,  G06Q10/04 ,  G06F17/13 ,  G06K9/62

Abstract: A composite time series forecasting model comprising a neural network sub-model and one or more state space sub-models corresponding to individual time series is trained. During training, output of the neural network sub-model is used to determine parameters of the state space sub-models, and a loss function is computed using the values of the time series and probabilistic values generated as output by the state space sub-models. A trained version of the composite model is stored.

公开(公告)号：US10748072B1

公开(公告)日：2020-08-18

申请号：US15153713

申请日：2016-05-12

Applicant: Amazon Technologies, Inc.

Inventor： Matthias Seeger ,  Gregory Michael Duncan ,  Jan Alexander Gasthaus

IPC: G06N7/00 ,  G06N20/00

Abstract: With respect to an input data set which contains observation records of a time series, a statistical model which utilizes a likelihood function comprising a latent function is generated. The latent function comprises a combination of a deterministic component and a random process. Parameters of the model are fitted using approximate Bayesian inference, and the model is used to generate probabilistic forecasts corresponding to the input data set.

公开(公告)号：US11120361B1

公开(公告)日：2021-09-14

申请号：US15441924

申请日：2017-02-24

Applicant: Amazon Technologies, Inc.

Inventor： Tim Januschowski ,  Joos-Hendrik Boese ,  Jan Alexander Gasthaus ,  Sebastian Schelter

IPC: G06N20/00 ,  G06N7/00

Abstract: An input data set with a plurality of item descriptors comprising respective time series observations is identified. A routing directive indicating a predicate to be evaluated to determine whether a particular item descriptor is to be included in a training data set for a first learning algorithm is obtained. A plurality of learning algorithms are trained using training data sets derived from the input data set according to respective routing directives, and the trained algorithms are stored.