公开(公告)号：US20180232661A1

公开(公告)日：2018-08-16

申请号：US15433680

申请日：2017-02-15

申请人： LinkedIn Corporation

发明人： Yi Li ,  Victor Chen ,  Krishnaram Kenthapadi ,  Ganesh Venkataraman

IPC分类号： G06N99/00 ,  G06F17/30 ,  G06F17/16 ,  G06N5/04

CPC分类号： G06N99/005 ,  G06F17/16 ,  G06F17/30598 ,  G06F17/30958 ,  G06K9/00 ,  G06K9/6219 ,  G06K9/6222 ,  G06K9/6261 ,  G06N5/04 ,  G06Q10/1053

摘要： The disclosed subject matter involves identifying clusters and segments of a population of data for use in a recommendation service. Clusters of members or items are formed, where the clusters, or partitions are close to being equal in size. Items are distributed based on similarities identified with matrix factorization. The items are formed into clusters based on the similarities and the clusters are used in training of a generalized linear mixed model treating the clusters as random-level effects. The trained model may be used in the recommendation service. Other embodiments are described and claimed.

公开(公告)号：US10262299B2

公开(公告)日：2019-04-16

申请号：US15433741

申请日：2017-02-15

申请人： LinkedIn Corporation

发明人： Yi Li ,  Victor Chen ,  Krishnaram Kenthapadi ,  Ganesh Venkataraman

IPC分类号： G06Q50/00 ,  G06Q10/10 ,  G06N99/00

摘要： The disclosed subject matter involves identifying clusters and segments of a population of data for use in a recommendation service. Clusters of members or items are formed, where the clusters, or partitions are close to being equal in size, items are distributed based on similarities identified with matrix factorization. A matrix used in the matrix factorization is customized based on the recommendation type. The items are formed into clusters based on the similarities and the clusters are used in training of a generalized linear mixed model treating the clusters as random-level effects. The trained model may be used in the recommendation service. Other embodiments are described and claimed.