公开(公告)号：US20230419396A1

公开(公告)日：2023-12-28

申请号：US17846474

申请日：2022-06-22

Applicant: eBay Inc.

Inventor： Stephanie Michelle Moyerman ,  Kishore Paul

IPC: G06Q30/08 ,  G06Q30/02 ,  G06Q30/06 ,  G06Q10/08 ,  G06K9/62

CPC classification number: G06Q30/08 ,  G06Q30/0283 ,  G06Q30/0271 ,  G06Q30/0641 ,  G06Q10/08345 ,  G06K9/6256

Abstract: Systems and methods are directed to using counterfactual machine-learning analysis to improve a probability of transaction conversion. The system trains a model with training data extracted from past transactions, whereby the model determines a probability for transaction conversion based in part on user account behavior. The system monitors the user account behavior associated with a potential buyer including tracking a first action performed involving an item of a listing. A user attribute associated with the user account and an item attribute associated with the item are determined. Based on the first action, the probability is determined by applying the user attribute, the item attribute, and the user account behavior to the model. Based on the probability being less than a conversion threshold, counterfactual analysis is performed to identify a change associated with the item that results in the probability exceeding the conversion threshold. The change may be automatically implemented.