Shopify Inc.

Niklas Itänen

Siavash Ghorbani

Peng Yu

Kyle Bruce Tate

Kshetrajna Raghavan

Xiaoxiao Li

Ivan Sanchez

Michael Schneider

Cameron Morgan

A data partitioning system receives an input dataset for e-commerce products, each sample containing attributes and associated values for each product including at least an image; represents each sample as a node on a graph to provide a graph of nodes for the dataset; measures a relative similarity distance between each pair of nodes based on comparing at least image values for the attributes; determines for each pair of nodes whether they are related if the similarity distance between them is below a defined threshold, and if related, generate an edge between them on the graph; group the connected nodes into a first or a second group such that the grouped nodes have no edges connecting them to nodes in the other group and have a shortest relative similarity distance with each other. The groups are used as training dataset and testing data sets for a supervised machine learning classifier.

Systems and methods for automated product classification

Methods and systems for subscription to retail browsing sessions. While two users are independently browsing the same merchant's store in parallel, the system may enable sharing or cross-sharing of commerce event data from a first user's browsing session to be injected into the other user's browsing session, so that the other user may follow along with the first user's browsing activity. The sharing may be dependent upon the first user enabling a live browse event and the other user subscribing to it. The sharing may be dependent upon subscribers having an active browsing session in the same merchant store as the first user's browsing session. To the extent that a subscribing user navigates to a different merchant or store, the sharing of commerce event data may be stopped or reduced to reflect the fact that the two users are no longer browsing the same merchant location in parallel.

Session subscription for commerce events

A customer may wish to purchase products with a lower associated carbon footprint when shipped, or may wish to know the cost associated with offsetting a product's carbon footprint in order to make informed decisions, while browsing and making purchases online. The computer is faced with the computational challenge of trying to determine a value indicative of the carbon emissions associated with shipping a package, before the package has even shipped. The computation may need to be performed during interactive scenarios, such as while browsing. A system and method are provided in order to present a customer with a carbon emissions indication relating to the shipment of a product without disrupting typical online activity.

Methods and systems for obtaining an indication of carbon emissions based on shipping route and transportation mode prediction

Growing community of inventors

Ottawa, Canada

Niklas Itänen