-
公开(公告)号:US09672474B2
公开(公告)日:2017-06-06
申请号:US14489449
申请日:2014-09-17
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Michael Brueckner , Ralf Herbrich
CPC classification number: G06N99/005
Abstract: Variables of observation records to be used to generate a machine learning model are identified as candidates for quantile binning transformations. In accordance with a particular concurrent binning plan generated for a particular variable, a plurality of quantile binning transformations are applied to the particular variable, including a first transformation with a first bin count and a second transformation with a different bin count. The first and second transformations result in the inclusion of respective parameters or weights for binned features in a parameter vector of the model. In a post-training phase run of the model, at least one parameter corresponding to a binned feature is used to generate a prediction.
-
公开(公告)号:US10318882B2
公开(公告)日:2019-06-11
申请号:US14484201
申请日:2014-09-11
Applicant: Amazon Technologies, Inc.
Inventor: Michael Brueckner , Daniel Blick
Abstract: An indication of a data source to be used to train a linear prediction model is obtained. The model is to generate predictions using respective parameters assigned to a plurality of features derived from observation records of the data source. The parameter values are stored in a parameter vector. During a particular learning iteration of the training phase of the model, one or more features for which parameters are to be added to the parameter vector are identified. In response to a triggering condition, parameters for one or more features are removed from the parameter vector based on an analysis of relative contributions of the features represented in the parameter vector to the model's predictions. After the parameters are removed, at least one parameter is added to the parameter vector.
-
公开(公告)号:US10977149B1
公开(公告)日:2021-04-13
申请号:US15925607
申请日:2018-03-19
Applicant: Amazon Technologies, Inc.
Inventor: Giovanni Zappella , Cédric Philippe Charles Jean Ghislain Archambeau , Edward Thomas Banti , Michael Brueckner , Borys Marchenko , Martin Milicic , Jurgen Ommen , Dmitrij Scsadej
IPC: G06F11/34 , G06F16/957
Abstract: A testing environment in which offline simulations can be run to identify policies and/or prediction models that result in more valuable content being included in content pages is described herein. For example, the offline simulations can be run in an application executed by an experiment device using data gathered by a production content delivery system. The simulation application can test any number of different policies and/or prediction models without impacting users that use a production content delivery system to request content.
-
-