Shopify Inc.

Peng Yu

Putra Manggala

Xinyi Zhao

Mladen Rangelov

Jingchuan Zhao

Brandon Chu

Kshetrajna Raghavan

Kyle Bruce Tate

Xiaoxiao Li

Siavash Ghorbani

Roni Gurvich

Niklas Itänen

Ali Kiyan Azarbar

Vahe Khachikyan

Niklas Itaenen

Siphumelele Langeni

George Yacoub

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

When a merchant ships a product to a buyer, the merchant may wish to push shipping status updates to the buyer. Moreover, the buyer may wish to receive a notification when a shipping event has occurred in order to remain informed regarding the shipping status of their package without actively checking the package's status with the carrier. In some embodiments, there is provided a computer-implemented system and method that obtains a tracking identifier for a package, transmits the tracking identifier to a carrier's computing interface (e.g. the carrier's API), receives back an indication of the most recent shipping event, predicts the time of a next shipping event at least based on the most recent shipping event, and retransmits the tracking identifier to the computing interface based on the predicted time of the next shipping event.

Methods and systems for smart API polling for predicted delivery events

A computer-implemented method and system for generating a blurred image from an original image. The method and system generate the blurred image using a process that enables fast efficient decoding of the compact encoded blurred image by a client device. The method may include transforming an original image to a block of coefficients in a frequency domain, low-pass filtering the block of coefficients in the frequency domain to produce a block of filtered coefficients, inverse transforming the block of filtered coefficients to produce a blurred image in a pixel domain, encoding the blurred image using a lossy-compression image encoder to produce an encoded blurred image, and transmitting the encoded blurred image to a client device for reconstruction and display by the client device.

Methods and devices for generating a blurred image

Computer-implemented methods and systems for colour-based image tagging and colour-based searching. The method may include identifying, using image analysis, one or more dominant colours of a product based on an image of the product and receiving selection of at least one of the one or more dominant colours. In response to receiving the selection of the at least one of the one or more dominant colours, a search for products matching the at least one of the one or more dominant colours may be initiated to obtain one or more results of the searching, the one or more results including at least one product matching the at least one of the one or more dominant colours.

Methods and systems for colour-based image analysis and search

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 managing an online application database and application search. Search queries for applications are received from users. Unfulfilled queries are stored in memory. The platform identifies one or more application features based on the search queries within the stored unfulfilled queries, and generates an application build recommendation specifying the one or more application features. The application build recommendation is output to one or more developer accounts. If a new application is received, the platform may determine whether the new application contains features that sufficiently correspond to the features in one of the application build recommendations. User accounts that submitted the unfulfilled queries that served as the basis for the matching application build recommendation may be notified of the availability of the new application.

Methods and systems for generating application build recommendations

Methods and systems for notifying users of new applications

Growing community of inventors

Montreal, Canada

Peng Yu