Shopify Inc.

Roni Gurvich

Peng Yu

Kshetrajna Raghavan

Shaked Dunay

Adam Malloul

A computer-implemented method and system for optimally retraining a supervised machine learning model based on newly received data. The method comprises receiving, from a requestor device, a new data set for updating a previously-trained model generated using a first training data set and tested using a first testing data set. Then, the new data set is checked for components having an association to both the first training data set and the first testing data set; and where such components are found, they are deleted. Once all of the components of the new data have been examined, remaining components of the new data set are assigned to one of the first training or testing data set in dependence upon a relationship connectivity therewith to form at least one of an updated testing and training data set for building the updated model.

System and method for automated construction of data sets for retraining a machine learning model

A computer application may aim to identify first and second 'matching' objects. The matching method cannot necessarily be based on how visually similar the two objects are to each other because two matching objects might be different and/or be visually different. Moreover, the images of the objects to be matched might not necessarily have metadata to assist in the matching. In some embodiments, a machine learning model may be trained using a set of digital images, each including two or more matching objects. Triplet loss training may be used, and each triplet may include: an image of a first object extracted from a first image, an image of an object that is visually similar to an image of a second object extracted from the first image, and an image of a third object extracted from a different image.

Systems and methods for training and using a machine learning model for matching objects

A computer-implemented is disclosed. The method includes: receiving, via a client device, a product search query; identifying a first product attribute based on query terms associated with the product search query; obtaining at least one search result matching the product search query; obtaining a set of product images associated with the at least one search result; for each of the product images, determining a respective level of confidence based on an estimation as to whether the product image is associated with the first product attribute; ranking the product images based on the levels of confidence; selecting at least a subset of the product images based on the ranking; and providing, via the client device, an indication of the at least one search result and the associated subset of product images.

Growing community of inventors

Ramat Gan, Israel

Roni Gurvich