Walmart Apollo, LLC

Maplebear Inc.

Chuanwei Ruan

Kannan Achan

Sushant Kumar

Da Xu

Evren Korpeoglu

Ramasubramanian Balasubramanian

Peng Qi

Kamiya Motwani

Venugopal Mani

An online concierge system uses a model to predict a user's interaction with an item, based on a user embedding for the user and an item embedding for the item. For the model to account for more recent interactions by users with items without retraining the model, the online concierge system generates updated item embeddings and updated user embeddings that account for the recent interactions by users with items. The online concierge system compares performance of the model using the updated item embeddings and the updated user embeddings relative to performance of the model using the existing item embeddings and user embeddings. If the performance of the model decreases, the online concierge system adjusts the updated user embeddings and the updated item embeddings based on the change in performance of the model. The adjusted updated user embeddings and adjusted updated item embeddings are stored for use by the model.

Incrementally updating embeddings for use in a machine learning model by accounting for effects of the updated embeddings on the machine learning model

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform generating one or more item relational graphs for one or more items based on historical user purchases; transforming, using spectral filtering, the one or more item relational graphs into one or more frequency signals to remove noise from the one or more frequency signals; constructing, using a machine learning model, one or more item pair label classifications for one or more item pairs of the one or more items; generating a respective similarity score for each of the one or more item pairs; outputting a top k results for the one or more item pairs ranked by the respective similarity scores; and re-ranking, using a re-ranking algorithm, the top k results of the one or more item pairs based on a user preference for display on a user interface of an electronic device of a user. Other embodiments are disclosed.

System and method for automatically generating similar items using spectral filtering

This application relates to apparatus and methods for automatically identifying substitute items. A computing device can generate matrix data that identifies connection values between a plurality of items. The matrix data may be generated based on the application of one or more machine learning algorithms to historical data identifying accepted or denied item substitutions. The computing device may then receive item data identifying at least one second item and at least one attribute of that second item. The computing device may generate a graph based on the matrix data and the item data to determine connection values between the second item and the plurality of first items. The computing device may then determine a substitute item (e.g., a replacement item) for the second item based on the connection values between the second item and the plurality of first items.

Methods and apparatus for item substitution

System and method for generating a ranked list are disclosed. A plurality of prior interactions for a first customer are received by a computing device. Each of the prior interactions includes a product interaction and time. A ranked list of item recommendations is generated based on the plurality of prior interactions. The ranked list of item recommendations is generated by a trained prediction model trained using temporal information embedded into a finite-dimensional vector space. The ranked list of item recommendations is output by the computing device.

Growing community of inventors

Sunnyvale, CA, United States of America

Chuanwei Ruan