Coupang, Corporation

Gil Ho Lee

Pankesh Bamotra

Systems and methods are provided for categorizing products using AI. One method comprises retrieving initial training data including products associated with one or more categories; pre-processing the initial training data to generate synthesized training data; generating a hierarchical model using the synthesized training data, the hierarchical model containing at least two layers of nodes below a root node; receiving information associated with a first uncategorized product; and receiving a request to predict a set of N categories with the highest N total probability scores. The method may further comprise predicting, using the hierarchical model, N categories of the first uncategorized product, by calculating total probability scores, and determining the N categories with the highest N total probability scores; sorting the first uncategorized product into the N categories associated with the nodes from the first and second layers having the highest total probability scores; and displaying the sorted first uncategorized product and its associated N categories on a user device associated with a user.

Computerized systems and methods for product categorization using artificial intelligence

Systems and methods are provided for dynamically adjusting payout to deliverers, comprising receiving a plurality of delivery orders, wherein each of the plurality of delivery orders is associated with a delivery address in a geographic region, and wherein the geographic region is associated with a plurality of configurations; determining a base fee for fulfilling the plurality of delivery orders in the geographic region based on the plurality of configurations associated with the geographic region; adjusting, using a pricing algorithm, the base fee for fulfilling the plurality of delivery orders based on the determined configurations; receiving one or more features associated with the plurality of delivery orders; and adjusting the adjusted base fee based on the received one or more features, wherein the pricing algorithm used to calculate the base fee is selected among a plurality of pricing algorithms based on the geographic region.

Computerized systems and methods for providing a dynamic pricing system

Systems and methods are provided for categorizing products using Al. One method comprises retrieving initial training data including products associated with one or more categories; pre-processing the initial training data to generate synthesized training data; generating a hierarchical model using the synthesized training data, the hierarchical model containing at least two layers of nodes below a root node; receiving information associated with a first uncategorized product; and receiving a request to predict a set of N categories with the highest N total probability scores. The method may further comprise predicting, using the hierarchical model, N categories of the first uncategorized product, by calculating total probability scores, and determining the N categories with the highest N total probability scores; sorting the first uncategorized product into the N categories associated with the nodes from the first and second layers having the highest total probability scores; and displaying the sorted first uncategorized product and its associated N categories on a user device associated with a user.

Growing community of inventors

Shanghai, China

Gil Ho Lee