Maplebear Inc.

Peng Qi

Changyao Chen

Weian Sheng

Ramasubramanian Balasubramanian

Chuanwei Ruan

Zhenbang Chen

Jingying Zhou

Sharath Rao Karikurve

Jeffrey Bernard Arnold

David Pal

Jonathan Gu

Rob Donnelly

Sumit Garg

Bill Lundberg

An online system trains a machine-learned lift prediction model configured as a neural network. The machine-learned lift prediction model can be used during the inference process to determine lift predictions for users and items associated with the online system. By configuring the lift prediction model as a neural network, the lift prediction model can capture and process information from users and items in various formats and more flexibly model users and items compared to existing methods. Moreover, the lift prediction model includes at least a first portion for generating control predictions and a second portion for generating treatment predictions, where the first portion and the second portion share a subset of parameters. The shared subset of parameters can capture information important for generating both control and treatment predictions even when the training data for a control group of users might be significantly smaller than that of the treatment group.

Machine-learned neural network architectures for incremental lift predictions using embeddings

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

Machine-learned neural network architectures for incremental lift predictions

An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Training a model to predict likelihoods of users performing an action after being presented with a content item

An online concierge system includes sponsored content items in an interface including different slots for displaying content items. A sponsored content item may be displayed in a single slot or in multiple adjacent slots. The online concierge system determines a content score for various sponsored content items indicating a likelihood of a user interacting with a sponsored content item and a position bias for slots in the interface indicating a likelihood of the user interacting with a slot independent of content in the slot. Position biases are different dependent on a number of slots in which a content item is displayed. The online concierge system generates a graph identifying potential placements of sponsored content items in slots by selecting content items in an order according to their content scores. Sponsored content items are positioned in slots according to a path through the graph that has the highest overall expected value.

Method, computer program product, and system for accounting for variable dimensions of content items when positioning content items in a user interface having slots for displaying content items

An online concierge system maintains a taxonomy associating one or more specific items offered by a warehouse with a generic item description. When the online concierge system receives a generic item description from a user for inclusion in an order, the online concierge system uses the taxonomy to select a set of items associated with the generic item description. Based on probabilities of the user purchasing various items of the set, the online concierge system selects an item of the set for inclusion in the order For example, the online concierge system selects an item of the set for which the user has a maximum probability of being purchased. Subsequently, the online concierge system displays an interface for the user that is prepopulated with information identifying the selected item of the set.

Selecting an item for inclusion in an order from a user of an online concierge system from a generic item description received from the user

An online concierge system maintains historical orders received from a user that include one or more items. For items included in one more historical orders, the online concierge system determines an interval between orders including an item, providing an indication of a frequency with which the user orders the item. When the online concierge system receives a request to create an order from the user, in response to an amount of time between a most recently received order including the item and a time when the request was received is within a threshold duration of the interval between orders including the item, the online concierge system selects an item from a category including the item. The selected item may be the item or an alternative item in the category. Subsequently, the online concierge system displays an interface for the user that is prepopulated with information identifying the selected item.

Growing community of inventors

Menlo Park, CA, United States of America

Peng Qi