Abstract: Video and audio from a computer simulation are processed by a machine learning engine to identify candidate segments of the simulation for use in a video summary of the simulation. Text input is then used to reinforce whether a candidate segment should be included in the video summary.

Abstract: System, process, and device configurations are provided for electronic game control for game rewards and target goal control. A method can include receiving a target goal for at least one user and controlling electronic game content presentation on a display. The method can also include detecting user actions relative to the electronic game content presentation, including monitoring presentation time of the electronic game content and evaluating the user actions relative to the target goal. The method can also include updating the electronic game content based on the target goal and game presentation time, and generating a reward for target goal completion. Systems and processes described herein may be used for behavior modification, such as limiting playtime of electronic content. Systems and processes described herein may also be used to providing a training function for electronic games that includes user set goals for self-improvement.

Abstract: System, process, and device configurations are provided for dynamic chat translation and interactive game control. Methods can include receiving communications for a user of an electronic game and converting communications using a localization setting and a machine learning model for language processing to replace one or more segments of the communication. Updated communications may be output with replacement segments to provide automatic conversion of information in a user's understanding. By automatically adapting outputting voice or text of a game chat and/or game output, such as non-player character (NPC) chat, users may have improved understanding. In addition, systems and methods include detecting user reactions, including use of eye tracking data, to assess communication conversion and to update processes and models for conversion of communications.

Abstract: An online system performs an atypical replacement recommendation task in conjunction with a model serving system or the interface system to make recommendations to a user for replacing a target item with an atypical replacement item. The online system receives a search query from a user and identifies a target item based on the search query. The online system identifies a set of candidate items for replacing the target item. The online system may select one or more atypical replacement items in the set of candidate items, and generate an explanation for each atypical replacement item. The explanation provides a reason for using the atypical replacement item to replace the target item. The online system provides the atypical replacement items and the corresponding explanations as a response to the search query.

Abstract: An online concierge system may determine recommended search terms for a user. The online concierge system may receive a request from a user to view a user interface configured to receive a search query. The online concierge system retrieves long-term activity data including previous search terms entered by the user while searching for items to add to an online shopping cart. For each previous search term, the online concierge system retrieves categorical search terms corresponding to one or more categories to which the previous search term was mapped. The online concierge system determines a set of nearby categorical search terms and sends, for display via a client device, the set of nearby categorical search terms as recommended search terms.

Abstract: 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.

Abstract: Content items are presented to users based on sensitivity scores indicating sensitivity levels of users to relevance of content items to queries. A system receives a query from a target user, retrieves a set of search results responsive to the query, and retrieves a set of content items, each of which has a relevance score to the query. The system applies a machine learning model to user data of the target user to output a sensitivity score, indicating a sensitivity level of the target user to relevance of content item to the query. The system then selects one or more content items based on the sensitivity score and the relevance scores of the content items, incorporates the selected content items into the search results, and sends the search results with the selected content items for display to the target user.

Abstract: An online concierge system scores candidate replacement items for an ordered item that is not available for delivery. A set of contextual features may be generated describing the user and/or the order in which the item is being replaced, enabling the recommended items to be evaluated with additional context and more-correctly evaluate whether a customer will accept a replacement item, particularly when the replacement item is selected by a picker or the online concierge system. In addition, as candidate replacement items may receive feedback from the customer in different contexts, during training the candidate items may be labeled with different values according to a hierarchy based on the particular feedback and context provided by the user.

Abstract: An online system trains a churn prediction model to attribute a churn event to one or more causal events. The churn prediction model receives customer features and online system features as inputs. Various causal events that occur affect one or more online system features. To avoid biasing the churn prediction model using input features that are related to possible causal events, the online system determines customer features and online system features based on customer interactions occurring in different time intervals. The customer features are determined from interactions in a time interval that is earlier than a time interval from which interactions are used to determine online system features. Such time segmenting decorrelates the features input to the model from the events, reducing potential bias from the causal events on the churn prediction model.

Abstract: A system or a method for fulfilling orders using a machine-learned model in an online system. When a user places an order, the system accesses a model trained on historical data, including characteristics of candidate locations, previous orders, and recent inventory records. The model predicts the probability that each candidate location will incompletely fulfill the order. The system selects the location with the lowest probability of incomplete fulfillment and sends fulfillment instructions to client devices of available shoppers. After the order is fulfilled, the system receives data from the client devices of shoppers, identifies whether the order was completely fulfilled, and updates the machine-learned model based on the actual outcomes.

Abstract: Based on logged information about prior events, an online concierge system generates a set of location metrics that quantify properties of locations such as retailers at which items may be acquired, and residences to which the items are brought. The location metrics can be used for a variety of purposes to aid customers or other users of the online concierge system, such as providing the users with more information (e.g., likely delivery delays) or alternative options (e.g., pricing options), or emphasizing options that the location metrics indicate would be of particular value to the user. To determine whether to emphasize a particular option, the online concierge system applies a machine-learned model that predicts whether emphasizing that option would effect a positive change in user behavior, relative to not emphasizing it.

Abstract: An online system provides a platform for users to place orders at different physical retailers. When a user moves from one location to another (e.g., the user physically moves or is traveling), where the user's preferred retailer is not available, the online system suggests a new retailer for the user and optionally items to purchase at the new retailer. When a user accesses the online system from a new location, the system obtains the user's previous purchases and computes a repurchase probability. The system then ranks candidate new retailers in the new location based on their match to the likely repurchased items. To suggest new items to buy at the new retailer, the system uses existing replacement models to suggest replacements for the items that the user is likely to buy based on previous purchases.

Abstract: 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.

Abstract: An online concierge system may determine recommended search terms for a user. The online concierge system may receive a request from a user to view a user interface configured to receive a search query. The online concierge system retrieves long-term activity data including previous search terms entered by the user while searching for items to add to an online shopping cart. For each previous search term, the online concierge system retrieves categorical search terms corresponding to one or more categories to which the previous search term was mapped. The online concierge system determines a set of nearby categorical search terms and sends, for display via a client device, the set of nearby categorical search terms as recommended search terms.

Abstract: In an online concierge system, a shopper retrieves items specified in an order by a customer from a retail location. The online concierge system optimizes order fulfillment by selecting a retail location for an order that is most time-efficient and that is most likely to have each of the item in the order available. Hence, the online concierge system may select a less convenient retail location that is more likely to have each item being ordered available. To predict whether a retail location incompletely fulfill the order if selected to fulfill the order, the online concierge system trains a machine learning model based on prior orders fulfilled by the retail location, a shopper retrieving items in the order, items in the order, and other features.

Abstract: An online system generates session-based recommendations for a user accessing an application of the online system. The online system receives, from one or more client devices, a sequence of actions performed by a user during a session of an application of an online system. The online system generates a sequence of tokens from the sequence of actions by tokenizing an action to a token representing a respective item identifier. The online system applies a transformer-based machine-learned model to the sequence of tokens to generate predictions for a set of items. The online system selects a subset of items based on the generated predictions for the set of items. The online system generates one or more recommendations to the user from the selected subset of items and displays the recommendations to the user.

Abstract: 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.

Abstract: A specific item is identified to suggest a replacement therefor to a user. A set of candidate replacement items for the specific item is determined. For at least one of the candidate replacement items, an expiration score is determined based on expiration information associated with the item. A replacement score for the candidate replacement item is determined by inputting the determined expiration score as a feature into a machine learning model that is trained using features of historical samples of candidate replacement items suggested as a replacement to users and the replacement suggestion being accepted by the users. One or more of the candidate replacement items is selected based on respective replacement scores as one or more suggested replacement items. A graphical user interface of a client device of the user is caused to display the one or more suggested replacement items as the replacement for the specific item.

Abstract: An online concierge system allows users to order items from a warehouse having multiple physical locations, allowing a user to order items at any given warehouse location. To select a warehouse location for a warehouse selected by a user, the online concierge system identifies a set of items that the user has a threshold likelihood of purchasing from prior orders by the user. For each of a set of warehouse locations, the online concierge system applies a machine-learned item availability model to each item of the identified set. From the availabilities of items of the set at each warehouse location of the set, the online concierge system selects a warehouse location. The online concierge system identifies an inventory of items from the selected warehouse location to the user for inclusion in an order.

Abstract: An online concierge shopping system identifies candidate items to a user for inclusion in an order based on prior user inclusion of items in orders and items currently included in the order. From a multi-dimensional tensor generated from cooccurrences of items in orders from various users, the online concierge system generates item embeddings and user embeddings in a common latent space by decomposing the multi-dimensional tensor. From items included in an order, the online concierge system generates an order embedding from item embeddings of the items included in the order. Scores for candidate items are determined based on similarity of item embeddings for the candidate items to the order embedding. Candidate items are selected based on their scores, with the selected candidate items identified to the user.