Abstract: Merchant quality may be inferred through machine learning techniques. A customer satisfaction classifier may receive data associated with a customer's engagement with a merchant, and may apply a machine learning model to the received data in order to infer a satisfaction of the customer with the merchant. The inferred satisfaction may be used to determine a rating of the merchant that is imputed to the customer.

Abstract: A service provider may obtain information about a plurality of items offered for acquisition by a merchant. The service provider may identify one or more items of the plurality of items that are the same as one or more respective items included in a catalog of items associated with the service provider. The items included in the catalog of items may be available for acquisition via the service provider. Additionally, the service provider may communicate with the merchant to offer services in relation to the items included in the service provider catalog of items that match the items offered by the merchant.

Abstract: Inactive areas of interest to a merchant delivery service may be identified and customers within those areas may be utilized to recruit eligible merchants to participate with a merchant delivery service so that the merchant delivery service can deliver customer ordered products on behalf of participating merchants to the customers within the area. In some implementations, the merchant delivery service may provide incentives to customer to incent the customers to recruit eligible merchants to participate with the merchant delivery service. Likewise, incentives may be provided to merchants to incent merchants to participate in the merchant delivery service. When an eligible merchant becomes a participating merchant, the merchant delivery service provides a reward to the customers that recruited the merchant.

Abstract: A merchant system including an order management application and method of integrating orders received from multiple ordering channels is described. An aggregated order queue is established including multiple orders from multiple different ordering channels. The orders are processed for fulfillment and a delivery channel is selected from multiple delivery channels for delivery of the one or more items of the order. The multiple orders, regardless of the ordering channel originating the order, and delivery channels may be managed via a single user interface.

Abstract: Management of persistent campaigns can be automated across multiple possible communication channels. A campaign management service monitors state information for the targeted users to ensure that the campaign content is provided to those users at appropriate times using appropriate channels. After a state change is detected for a particular user, corresponding to the desired action being taken, the campaign content will no longer provided for that user across any of those channels. The ability to manage state across all channels ensures that the providing of campaign content to any targeted users does not exceed frequency, occurrence, or other such criteria, and the types of actions can be any detectable actions performed with respect to an electronic environment.

Abstract: A merchant system including an order management application and method of integrating orders received from multiple ordering channels is described. An aggregated order queue is established including multiple orders from multiple different ordering channels. The orders are processed for fulfillment and a delivery channel is selected from multiple delivery channels for delivery of the one or more items of the order. The multiple orders, regardless of the ordering channel originating the order, and delivery channels may be managed via a single user interface.

Abstract: This disclosure describes, in part, techniques and systems for creating personalized travel itineraries for users. The personalized itineraries may be created by analyzing prior travel preferences of a user to suggest various locations, activities, time frames, transportation, and/or lodging to the user. In some instance, the personalized itineraries may be created by comparing data associated with the user with data associated with a group of other users to determine a similarity between the user and other users within the group of other users. Where a similarity exists, an itinerary provider may create an itinerary for the user based on the travel preferences of the user and the prior behavior of the similar users.

Abstract: Customers may place orders for items for delivery, where merchants provide the items, and a service provider receives the orders and facilitates the delivery of the items. Upon receiving multiple orders, the orders may be prioritized based on users scores associated with users that placed the orders. An order objective for the orders may be determined and multiple fulfillment plans for each order may be generated. For a particular order, a fulfillment plan of the multiple fulfillment plans may be selected based on the order objective for that order, where the selected fulfillment plan may govern how and when the items included in the order are to be delivered to the user that placed the order. The service provider may cause the items associated with the order to be delivered to the user pursuant to the selected fulfillment plan.

Abstract: A customer may specify, via a mobile device, a current location at which the customer desires to receive a delivery order for food items, as well as a preferred amount of time for the delivery. In response, food items that are available to be delivered to the current location within the preferred amount of time are identified and presented to the customer, including food items to be prepared/provided by merchants and food items current being transported by deliverers within sophisticated food item containers and/or delivery containers. Upon receiving a selection of one or more food items, a delivery of the ordered/selected food items may be facilitated. For instance, one or more instructions to prepare and/or transport the food item(s) may be transmitted to devices of merchants and/or deliverers.

Abstract: Various systems, methods and other embodiments are provided for generating offers for the purchase of products. In one embodiment, transaction data is stored in a data store. The transaction data comprises a record of a plurality of transactions for the purchase of products through a plurality of channels of commerce. Requests are received in a server from clients for an offer in association with an interaction involving a product. Each request includes a tag indicating at least one of the channels of commerce associated with the interaction. For each request, an offer is generated in response to the request, the offer being specific to the at least one of the channels of commerce.

Abstract: Implicit occasion personalization is described. A service provider may access user data associated with users corresponding to the user devices. The user data may represent user interactions with a plurality of entities that each offer one or more services. The service provider may determine a user pattern associated with a user of the plurality of users and may determine, from the user pattern, that the user is likely to request and/or receive the one or more services on a date. The service provider may generate a recommendation including at least one of a deal associated with the one or more services or a reservation on the date to the individual user on or before the date.

Abstract: Customers may place orders for items for delivery, where merchants provide the items, and a service provider receives the orders and facilitates the delivery of the items. Upon receiving multiple orders, the orders may be prioritized based on users scores associated with users that placed the orders. An order objective for the orders may be determined and multiple fulfillment plans for each order may be generated. For a particular order, a fulfillment plan of the multiple fulfillment plans may be selected based on the order objective for that order, where the selected fulfillment plan may govern how and when the items included in the order are to be delivered to the user that placed the order. The service provider may cause the items associated with the order to be delivered to the user pursuant to the selected fulfillment plan.

Abstract: A food item container that contains a food item may include one or more sensors that collect sensor data indicating a characteristic (e.g., temperature, humidity, pressure, orientation, etc.) associated with the food item. A delivery container that transports the food items within the food item container may also include one or more sensors that collect the sensor data. Based on the sensor data, a component of the food item container and/or the delivery container may maintain or adjust the characteristic. The one or more sensors of the delivery container may also detect an identifier associated with the food item container, which may indicate which food item containers (and corresponding food items) are included within each delivery container.

Abstract: The systems and processes discussed herein may identify, prioritize, and recommend new deals to consumers based at least in part on triggering events. A consumer may interact with a previously acquired deal, such as by redeeming the deal, requesting a refund for the deal, etc. Such user interaction may be determined to be a triggering event. Based on a type of the triggering event, the systems described herein may identify one or more new deals having characteristics similar to the previously acquired deal. The one or more new deals may be recommended to a user at the same time or at some time after the triggering event occurs via a website, an e-mail message, an application associated with a user device, a text message, or any other manner that may be used to communicate the new deals to the user.

Abstract: Personalizing recommendations for users based at least in part on learning user patterns that are specific to individual entities is described. A service provider may determine data associated with interactions between users and an entity and may determine, based on the data, patterns associated with a user of the users and the entity. The patterns may represent affinities between the user and at least one of goods or services offered by the entity. The service provider may determine entity data associated with the entity and, based at least in part on an availability of at least one of the goods or the services, may generate recommendations associated with the patterns and the entity data.

Abstract: A meal ordering service is configured to receive takeout and delivery orders from customers and to place the orders with selected restaurants. Past information regarding a customer is collected and analyzed to create a predictive model of the customer's meal ordering habits. On any given day, the predictive model may be used, in light of the current and scheduled status of the customer, to predict a time of day that the customer may want to receive a meal and to also determine a restaurant from which the customer may want to receive the meal. The meal ordering service may be configured to automatically order a meal for the customer from the determined restaurant so that the meal arrives at or before the predicted time of day.

Abstract: A service provider may obtain information about a plurality of items offered for acquisition by a merchant. The service provider may identify one or more items of the plurality of items that are the same as one or more respective items included in a catalog of items associated with the service provider. The items included in the catalog of items may be available for acquisition via the service provider. Additionally, the service provider may communicate with the merchant to offer services in relation to the items included in the service provider catalog of items that match the items offered by the merchant.

Abstract: A merchant system including an order management application and method of integrating orders received from multiple ordering channels is described. An aggregated order queue is established including multiple orders from multiple different ordering channels. The orders are processed for fulfillment and a delivery channel is selected from multiple delivery channels for delivery of the one or more items of the order. The multiple orders, regardless of the ordering channel originating the order, and delivery channels may be managed via a single user interface.

Abstract: This disclosure is generally directed to providing access to media content for travelers during a trip, where the trip may include lodging, transit, and/or activities. A service provider may obtain information about a user and a trip. The service provider may determine information about the user, such as account information that may identify media content that is typically accessible by the user. An amount of available space on a device may be determined that can be used to store prefetched content for the trip. Recommended content may be selected to fill the amount of space on the device. The recommended content may be based on information about the user, information about the trip, and/or other information. The recommended content may be downloaded onto the device prior to the trip so that the user has access to the content from the device during the trip.

Abstract: Location data may be obtained through devices associated with one or more users. The actual locations and places that correspond to the location data may be inferred. Location patterns that represent when and where each user spends their time may also be determined. One or more personas that represent categories corresponding to types of behavior or location patterns that users may exhibit may be created and maintained. One or more of the personas may be assigned to or associated with each of the users based on the location patterns associated with each user and the type of behavior that is expected to be exhibited for each persona. One or more recommendations may be provided to the users based at least partly on the personas that have been assigned to the users, which may cause the users to receive recommendations that are likely to be of particular interest.