Coupang, Corporation

Sap Se

Zonghan Wu

Wei Wei

Ping Yin

Min Woo Lee

Sheng Meng

Edward Lu

Jessica Yang

Jia Feng

Fangling Liu

Ruibin Zhang

Yong Zang

Timothy Schoenharl

Liwen He

Xuejian Qiao

Pil Su Kim

Yan Fan

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.

Computerized systems and methods for predicting and managing scrap

Methods and systems for determining a cause of out of stock condition by running a decision tree against historical information associated with the out of stock item and contacting a supplier of the out of stock item to request items based on the determined cause. The system receives information associated with an out of stock item from a system storing information associated with items in a fulfillment center, the information collected over an extended period, determines a cause of the out of stock condition by running a decision tree against the received information, the decision tree includes a plurality of conditions, and predicts an out of stock condition of the item based on the determined cause. Based on the prediction, the system contacts a supplier of the out of stock item to request more items.

Computer-implemented systems and methods for intelligent prediction of out of stock items and proactive reordering

Refresh requests are received by a data source that each request a snapshot of current members of one of a plurality of dynamically changing groups and dynamically changing rules corresponding to such group. Thereafter, the data source queues the received plurality of refresh requests for selective execution or deletion into a new request queue. In addition, real-time execution of refresh jobs are initiated for all of queued refresh requests if a number of refresh requests in both of the new request queue and a waiting requests queue is below a pre-defined threshold. Alternatively, a job framework schedules execution of task jobs for a subset of the queued requests in the new request queue and the waiting requests queue if certain conditions are met.

Refreshing framework

Growing community of inventors

Shanghai, China

Zonghan Wu