Maplebear Inc.

Ramasubramanian Balasubramanian

Saurav Manchanda

Omar Rogelio Alonso

Peng Qi

Chuanwei Ruan

Girija Narlikar

Sharath Rao Karikurve

Ashish Sinha

Lukasz Czekaj

Joseph Olivier

Lynn Fink

Michael Prescott

Sanam Alavizadeh

Jeong Eun Woo

Alexandra Hart

Lauren Scully

Daniel Summerhays

Nicole Yin Chuen Lee Altman

Samuel Lederer

Anna Vitti

An online concierge system receives, from a client device associated with a user of the online concierge system, order data associated with an order placed with the online concierge system, in which the order data describes a delivery location for the order. The online concierge system receives information describing a set of attributes associated with the delivery location and accesses a machine learning model trained to predict a difference between an arrival time and a delivery time for the delivery location. The online concierge system applies the model to the set of attributes associated with the delivery location to predict the difference between the arrival time and the delivery time for the delivery location and determines an estimated delivery time for the order based at least in part on the predicted difference. The online concierge system sends the estimated delivery time for the order for display to the client device.

Delivery time estimation using an attribute-based prediction of a difference between an arrival time and a delivery time for a delivery location

An online concierge system uses a machine learning click through rate model to select promoted items based on user embeddings, item embeddings, and search query embeddings. Embeddings obtained by an embedding model may be used as inputs to the click through rate model. The embedding model may be trained using different actions to score the strength of a customer interaction with an item. For example, a customer purchasing an item may be a stronger signal than a customer placing an item in a shopping cart, which in turn may be a stronger signal than a customer clicking on an item. The online concierge system generates a ranking of candidate promoted items based on the search query and using the click through rate model. Based on the ranking, the online concierge system displays promoted items along with the organic search results to the customer.

Machine learning model for click through rate predication using three vector representations

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

An online concierge system generates recipe embeddings for recipes including multiple items and user embeddings for users, with the recipe embeddings and user embeddings in a common latent space. To generate the user embeddings and the recipe embeddings, a model includes separate layers for a user model outputting user embeddings and for a recipe model outputting recipe embeddings. When training the model, a weight matrix generates a predicted dietary preference type for a user embedding and for a recipe embedding and adjusts the user model or the recipe model based on differences between the predicted dietary preference type and a dietary preference type applied to the user embedding and to the recipe embedding. Additionally cross-modal layers generate a predicted user embedding from a recipe embedding and generate a predicted recipe embedding from a user embedding that are used to further refine the user model and the recipe model.

Method, computer program product, and system for training a machine learning model to generate user embeddings and recipe embeddings in a common latent space for recommending one or more recipes to a user

An online concierge system selects content for presentation to a user by using a product scoring engine. The product scoring engine generates a user embedding for user data and a query embedding for query data. The product scoring engine generates an anchor embedding based on the user embedding and the query embedding, where the anchor embedding is an embedding in a product embedding space. The product scoring engine compares the anchor embedding to a set of product embeddings to score a set of products for presentation to a user.

Non-transitory computer-readable medium, and method for context-based content-scoring for an online concierge system

An online concierge system suggests replacement items when an ordered item may be unavailable. To promote similarity of sources between the replacement item with the ordered item, candidate replacement items are scored, in part, based on a source similarity score based on a source of the candidate replacement item and a source of the ordered item. The source similarity score may be determined by a computer model based on user interactions with item sources. The similarity score may be based on source embeddings that may be determined based on respective item embeddings or may be determined by training source embeddings directly from user-source interactions. The similarity score for a candidate replacement item may be combined with a replacement score indicating the user's likelihood of selecting the candidate replacement item as a replacement to yield a total score for selection as suggestion as a replacement for the ordered item.

Identifying candidate replacement items with a source similarity score

An online concierge system uses a cumulative incrementality score to evaluate the performance of incrementality models used by the online concierge system to identify users for treatment. The online concierge system applies an incrementality model to a set of examples to generate predicted incrementality scores for the examples. The online concierge system ranks the examples based on the predicted incrementality scores for the examples and groups the examples based on their rankings. The online concierge system iteratively computes cumulative incrementality scores for each grouping based on the examples of each grouping, and computes a final cumulative incrementality score for the incrementality model based on each of the cumulative incrementality scores.

Cumulative incrementality scores for evaluating the performance of machine learning models

Machine learning model for click through rate prediction using three vector representations

An online concierge system uses a domain-adaptive suggestion module to score products that may be presented to a user as suggestions in response to a user's search query. The domain-adaptive suggestion module receives data that is relevant to scoring products as suggestions in response to a search query. The domain-adaptive suggestion module uses one or more domain-neutral representation models to generate a domain-neutral representation of the received data. The domain-neutral representation is a featurized representation of the received data that can be used by machine-learning models in the search domain or the suggestion domain. The domain-adaptive suggestion module then scores products by applying one or more machine-learning models to domain-neutral representations generated based on those products. By using domain-neutral representations, the domain-adaptive suggestion module can be trained based on training examples from a similar prediction task in a different domain.

Growing community of inventors

San Francisco, CA, United States of America

Ramasubramanian Balasubramanian