公开(公告)号：US11556945B1

公开(公告)日：2023-01-17

申请号：US15714816

申请日：2017-09-25

Applicant: Amazon Technologies, Inc.

Inventor： Karthik Sundaresan Gurumoorthy ,  Vineet Shashikant Chaoji ,  Dinesh Mandalapu ,  Rajeev Ramnarain Rastogi

IPC: G06Q30/02 ,  G06Q10/06

Abstract: Systems and methods are disclosed to implement an item metric prediction system that predicts a metric for an item using a feature-based model built using other similar items. In embodiments, the system is used to predict item influence values (IIVs) of items indicating an expected amount of subsequent transactions that is caused by an initial transaction of the items. In embodiments, a sample of item transaction data is distributed to a plurality of task nodes, which execute in parallel to determine the items' observed IIVs from the transaction data. Subsequently, a new IIV is determined for an item whose observed IIV has a low confidence level. A set of similar items is selected, and a set of parameters of a feature-based model are tuned to fit the model to the observed IIVs of the similar items. A new IIV having a high confidence level is then obtained using the model.

公开(公告)号：US11210684B1

公开(公告)日：2021-12-28

申请号：US15873692

申请日：2018-01-17

Applicant: Amazon Technologies, Inc.

Inventor： Pranav Garg ,  Vineet Shashikant Chaoji ,  Karthik Sundaresan Gurumoorthy

IPC: G06Q30/02 ,  G06F17/18 ,  G06Q10/04

Abstract: Methods, systems, and computer-readable media for accurately estimating causal effects for related events are disclosed. A plurality of estimates of causal effects of events are determined. The estimates are determined independently. A subset of the estimates are determined not to satisfy a relationship among the causal effects. A set of accurate estimates are generated based at least in part on the subset of the estimates. The accurate estimates are generated using a smoothing process, and the accurate estimates satisfy the relationship.