公开(公告)号：US20220309562A1

公开(公告)日：2022-09-29

申请号：US17839934

申请日：2022-06-14

申请人： Mercari, Inc.

发明人： BYONG MOK OH ,  Takuma YAMAGUCHI ,  Rishabh Kumar SHRIVASTAVA ,  Fritz Mikio KURIBAYASHI ,  John Alexander LAGERLING ,  Minami TANAKA

IPC分类号： G06Q30/06 ,  G06N7/00 ,  G06N3/08 ,  G06Q30/02

摘要： Disclosed herein are embodiments for intelligent listing creation for a for sale object (FSO). Some embodiments operate by determining a numerical identifier corresponding to a category of the FSO. A binarization of the numerical identifier using hot encoding is performed and using a neural network regression model, an optimal offer price is generated based on a category of the FSO. Information about the FSO is provided to the neural network regression model that tokenizes the textual input, and a unique binary vector representing the category is provided instead of the numerical identifier to the neural network regression model. An optimal price, generated by the neural network regression model, based on the unique binary vector representing the category.

公开(公告)号：US20210406937A1

公开(公告)日：2021-12-30

申请号：US16912401

申请日：2020-06-25

申请人： Mercari, Inc.

发明人： Byong Mok OH ,  Takuma YAMAGUCHI ,  Rishabh Kumar SHRIVASTAVA ,  Fritz Mikio KURIBAYASHI ,  John Alexander LAGERLING ,  Minami TANAKA

IPC分类号： G06Q30/02 ,  G06Q30/06 ,  G06N3/04 ,  G06N3/08

摘要： Disclosed herein are embodiments for automated intelligent price guidance of listings for a for sale object (FSO) being offered by a seller. Some embodiments may operate by: receiving information relating to the FSO, including specifications for selling the FSO, wherein the specifications include an original offer price and a time window for selling the FSO; determining a category of the FSO; generating an optimal offer price for the FSO based on one or more of: (a) past listings of previously sold FSOs that have a same or similar category of the FSO; (b) the specifications, including the time window; (c) a category decay curve applicable to the category; and (d) seller flexibility curve of the seller; and through the use of a machine learning neural networking analysis suggesting the optimal offer price to the seller as an offer price for a listing corresponding to the FSO, wherein this price is evaluated over time and suggestions are made accordingly.

公开(公告)号：US20210406988A1

公开(公告)日：2021-12-30

申请号：US16912411

申请日：2020-06-25

申请人： Mercari, Inc.

发明人： Byong Mok OH ,  Takuma YAMAGUCHI ,  Rishabh Kumar SHRIVASTAVA ,  Mikio Fritz KURIBAYASHI ,  John Alexander LAGERLING ,  Minami TANAKA

IPC分类号： G06Q30/06 ,  G06Q30/02 ,  G06N3/08 ,  G06N5/04 ,  G06N7/00

摘要： Disclosed herein are embodiments for automatic, intelligent generation of listings for a for sale object (FSO) being offered by a seller. Some embodiments operate by: receiving information relating to the FSO, including specifications for selling the FSO and an election of an automatic listing option; determining a category of the FSO; generating an optimal offer price based on at least the category; and generating multiple listings for the FSO, wherein the multiple listings have varying titles, descriptions, pictures and offer prices.