-
公开(公告)号：US11853388B1
公开(公告)日：2023-12-26
申请号：US16562168
申请日：2019-09-05
Applicant: Amazon Technologies, Inc.
Inventor： Ramesh Natarajan , Kamalakannan Elangovan , Sravan Kumar Kasturi , James Kingsbery
CPC classification number: G06F17/18 , G06F17/156
Abstract: Devices and techniques are generally described for determining a recalibration frequency of a state space model. In various examples, a first hyperparameter for a first dataset may be determined. A residual value between a first data point of the first dataset and a machine learning model fitted to the first dataset may be determined. A plurality of second datasets may be generated based on the residual value. Second hyperparameters may be determined for the plurality of second datasets. A variability of the second hyperparameters may be determined. A third hyperparameter may be determined for a subset of the first dataset. A recalibration frequency may be determined for the machine learning model by comparing the third hyperparameter to the variability of the second hyperparameters.
-
公开(公告)号：US11775886B2
公开(公告)日：2023-10-03
申请号：US16218319
申请日：2018-12-12
Applicant: Amazon Technologies, Inc.
Inventor： Ramesh Natarajan , Jonathan Hosking
IPC: G06Q10/04 , G06F16/906 , G06Q10/0637 , G06F18/214 , G06F18/20
CPC classification number: G06Q10/04 , G06F16/906 , G06F18/2148 , G06F18/29 , G06Q10/06375
Abstract: A data set comprising records of state change events of items of an item collection, as well as records of asynchronous operations associated with the items, is obtained. The numbers of records in the data set may differ from one item to another. Using the data set, a Bayesian forecasting model employing a deconvolution algorithm is trained. The model generates estimates of metrics of a type of asynchronous operation using a combination of a category-level distribution of the asynchronous operation, an item-level distribution, and a category-versus item adjustment. A trained version of the model is stored.
-
公开(公告)号：US10558767B1
公开(公告)日：2020-02-11
申请号：US15461382
申请日：2017-03-16
Applicant: Amazon Technologies, Inc.
Inventor： Ramesh Natarajan , Jonathan Richard Morley Hosking
Abstract: Systems are provided to estimate autoregressive moving average (ARMA) models using maximum likelihood estimation and analytical derivatives, and to use such models for forecasting. The evaluation of the analytical derivatives during estimation of the model parameters may be performed using a state space representation with certain characteristics. An ARMA model estimated using maximum likelihood estimation, analytical derivatives, and the state space representation with certain characteristics can be used to forecast/predict values that are likely to occur in the future, given some set of previously-occurring values.
-
公开(公告)号：US10318874B1
公开(公告)日：2019-06-11
申请号：US14662021
申请日：2015-03-18
Applicant: Amazon Technologies, Inc.
Inventor： Gregory Michael Duncan , Ramesh Natarajan
Abstract: Corresponding to each forecasting model of a family of related models for a time series sequence, a respective state space representation is generated. One or more cross-validation iterations are then executed for each model of the family. In a given iteration, a training variant of the time series sequence is generated, with a subset of the time series sequence entries replaced by representations of missing values. Predictions for the missing values are obtained using the state space representation and the training variant, and a model quality metric is obtained based on prediction errors. The optimal model of the family is selected using the model quality metrics obtained from the cross validation iterations.
-
-
-
Search Results
4
records
(took 0.013 seconds)
