公开(公告)号：US20210090022A1

公开(公告)日：2021-03-25

申请号：US16849143

申请日：2020-04-15

Applicant: COUPANG CORP.

Inventor： Wei WEI ,  Guangyao ZHANG ,  Yong ZANG ,  Timothy SCHOENHARL

IPC: G06Q10/08 ,  G06Q30/06

Abstract: A computer-implemented systems and methods for intelligent generation of purchase orders is disclosed. The system may be configured to execute instructions for: receiving one or more demand forecast quantities of one or more products, the products corresponding to one or more product identifiers, and the demand forecast quantities comprising a demand forecast quantity for each product for each unit of time; receiving supplier statistics data for one or more suppliers, the suppliers being associated with a portion of the products; receiving current product inventory levels and currently ordered quantities of the products; determining preliminary order quantities for the products; constraining the preliminary order quantities to obtain recommended order quantities based at least on the supplier statistics data, the current product inventory levels, and the currently ordered quantities; and generating purchase orders to the suppliers for the products based on the recommended order quantities.

公开(公告)号：US20220188846A1

公开(公告)日：2022-06-16

申请号：US17546250

申请日：2021-12-09

Applicant: COUPANG CORP.

Inventor： Zonghan WU ,  Timothy SCHOENHARL ,  Wei WEI ,  Sheng MENG ,  Ping YIN

IPC: G06Q30/02 ,  G06N3/02

Abstract: Systems and methods for predicting that a stock keeping unit (SKU) is likely to be scrapped and performing preventative actions accordingly. The system receives a request to initiate a process related to predicting scrap likelihood associated with a plurality of SKUs, inputs data associated with each SKU into a trained prediction model, outputs, from the trained prediction model, a prediction value for each SKU, measures the trained prediction model by calculating a set of values, and generates a matrix comprising the calculated set of values. Using the matrix, a threshold prediction value is determined, and each SKU prediction value is compared to the threshold prediction value. Based on the comparison, a SKU of the plurality of SKUs is predicted as likely to be scrapped and at least one of a plurality of preventative actions is performed.