Abstract: Various processes are disclosed for discovering item relationships between particular items, such as products represented in an electronic catalog, based on monitored user behaviors (e.g., item viewing activities, item purchases, shopping cart activities, etc.). The discovered item relationships may, for example, be used to generate personalized item recommendations for users, and/or to supplement item detail pages of an electronic catalog with lists of related items. Also disclosed are processes for generating personalized item recommendations based on users' search activities and browse node visits.

Abstract: Methods and systems for providing multiple level text cloud navigation are described, where various categories are displayed in a first text cloud and, when a category is selected, a second text cloud is displayed having child nodes of the selected category and selected lower level nodes. The categories, child nodes, and selected other nodes are displayed using an importance identifier indicative of the number of results in that category or node, a relative importance thereof, a similarities metric, a recommendations metric, or the like.

Abstract: Various processes are disclosed for discovering item relationships between particular items, such as products represented in an electronic catalog, based on monitored user behaviors (e.g., item viewing activities, item purchases, shopping cart activities, etc.). The discovered item relationships may, for example, be used to generate personalized item recommendations for users, and/or to supplement item detail pages of an electronic catalog with lists of related items. Also disclosed are processes for generating personalized item recommendations based on users' search activities and browse node visits.

Abstract: A system is provided that extrapolates item characteristics from items considered to possess a characteristic to items not known to possess the characteristic. The system may include an item data repository that stores data representing physical items. These items can include first items having a characteristic and second items not known to have the characteristic. A characteristic extrapolation module can extrapolate the characteristic from at least some of the first items to at least some of the second items based at least in part on the strength of associations between the plurality of items. A recommendations module may provide item recommendations based at least partly on the characteristic of the items.

Abstract: A method of providing recommendations is disclosed and includes receiving a selection of an offering via an online site. The method also includes outputting a detail page related to the offering via the online site. The detail page includes a first selectable indicator corresponding to a social network of a visitor and a second selectable indicator corresponding to unfiltered content. The method also includes outputting at least one recommendation via the detail page. Each recommendation is associated with a member of the social network when input received via the online site indicates a selection of the first selectable indicator.

Abstract: A system is provided that extrapolates item characteristics from items considered to possess a characteristic to items not known to possess the characteristic. The system may include an item data repository that stores data representing physical items. These items can include first items having a characteristic and second items not known to have the characteristic. A characteristic extrapolation module can extrapolate the characteristic from at least some of the first items to at least some of the second items based at least in part on the strength of associations between the plurality of items. A recommendations module may provide item recommendations based at least partly on the characteristic of the items.

Abstract: Items, such as produce items, may be placed in containers, imaged, weighed, and stored for subsequent retrieval. Images that depict the items and attributes associated with the items may be presented to customers via an interface. Upon receiving an indication that a customer has purchased one or more items via the interface, a container that includes the one or more items is retrieved. The one or more items are removed from the container and packaged for delivery to the customer. The resulting empty container is refilled with new items, which are then imaged, weighed, and stored.

Abstract: Various processes are disclosed for discovering item relationships between particular items, such as products represented in an electronic catalog, based on monitored user behaviors (e.g., item viewing activities, item purchases, shopping cart activities, etc.). The discovered item relationships may, for example, be used to generate personalized item recommendations for users, and/or to supplement item detail pages of an electronic catalog with lists of related items. Also disclosed are processes for generating personalized item recommendations based on users' search activities and browse node visits.

Abstract: A multi-level approach for generating suggestions and/or recommendations associated with one or more items is provided. A group of related items may be identified, for example, by generating a collaborative filtering graph or other graph that includes items and connections between the items. Description data associated with items included in the group may be evaluated in order to determine respective keywords associated with the items and/or a list of common keywords representative of the group of items or a subset of the group of items. Based at least in part upon the list of common keywords, at least one suggestion may be generated.

Abstract: Relative ranking of items is performed based on a subjective attribute of the items. A user interface that displays the relative ranking of the items includes an axis that corresponds to the subject attribute. The user interface further includes a display section that displays representations of the items along the axis according to rankings relative to the subjective attribute. The display section is also to present one or more additional items in response to customer input.

Abstract: At an artificial intelligence service, a first group of attributes of data items, which can be represented in the same encoding space as a second group of attributes of class descriptors, is identified. Feature data structures are generated that respectively represent (a) the first group of attributes of an unlabeled subset of the data items and (b) the second group of attributes of the class descriptors. In one or more training iterations, a class-weights data structure that meets a quality criterion is computed, where the computations of at least one iteration include generating an aggregate data structure from the feature data structures. The class-weights data structure is stored.

Abstract: Techniques for analyzing recommendations may be described. In particular, an item offered from a network-based resource may be selected based at least in part on past orders for the item. Recommended items offered from the network-based resource may also be identified. A determination may be made as to whether the recommended items may include the item. Based on this determination, an indication of an issue associated with recommending the item may be generated. Based on the indication, a workflow to identify a potential cause of the issue may be initiated.

Abstract: Techniques for performing outputting additional content associated with but nonresponsive to an input command are described. A system receives input data from a device. The system determines an intent representing the input data and receives first output data responsive to the input data. The system determines, based on context data, that additional content associated with the first output data but nonresponsive to the input data should be output. The system receives second output data associated with but nonresponsive to the input data thereafter. The system then presents first content corresponding to the first output data and second content corresponding to the second output data.

Abstract: A computer system for detecting associations between items may include a probabilistic analysis component that accesses user data having information about item selections by a plurality of users. The probabilistic analysis component may programmatically generate associations between certain items by determining a first number of users who selected the items and by estimating a probability that a second number of users would have selected the items due to random chance. The probabilistic analysis component may estimate this probability based at least partly on a number of item selections made by one or more of the users.

Abstract: This disclosure describes systems and methods for recommending bundles of items to users. A bundle can include an item that is substitutable for an item selected by a user and one or more related items that complement the substitutable item. For example, if a user has selected a wireless device on a page of a network application, a bundle recommendation can be provided that includes a similar wireless device and related accessories, a compatible service plan, and the like. Recommending bundles of items can be beneficial for providing users with access to items that they might like to purchase together, without requiring users to separately find each item.

Abstract: Various processes are disclosed for discovering item relationships between particular items, such as products represented in an electronic catalog, based on monitored user behaviors (e.g., item viewing activities, item purchases, shopping cart activities, etc.). The discovered item relationships may, for example, be used to generate personalized item recommendations for users, and/or to supplement item detail pages of an electronic catalog with lists of related items. Also disclosed are processes for generating personalized item recommendations based on users' search activities and browse node visits.

Abstract: A method of providing recommendations is disclosed and includes receiving a selection of an offering via an online site. The method also includes outputting a detail page related to the offering via the online site. The detail page includes a first selectable indicator corresponding to a social network of a visitor and a second selectable indicator corresponding to unfiltered content. The method also includes outputting at least one recommendation via the detail page. Each recommendation is associated with a member of the social network when input received via the online site indicates a selection of the first selectable indicator.

Abstract: A complementary item promoter user interface (UI) is provided that promotes, to a user, items that are complementary to an item of interest to the user. Upon the user's selection of an item of interest, the complementary item promoter UI presents a combination of complementary items selected in accordance with business rules data. The business rules data may be submitted by an administrative user to a content management service that deploys the complementary item promoter UI in a deployment environment. The business rules data may include rules that govern how complementary items are chosen or how they are to be displayed in the complementary item promoter UI.

Abstract: Architectures and techniques are described to provide customized versions of electronic books with various supplemental content items. The electronic books include a framework having core content that is provided with each electronic book and supplemental content portions that are populated with supplemental content items based on the preferences of particular readers of the electronic books. In some cases, the electronic books may include supplemental content options that are selectable to provide access to supplemental content items by readers of the electronic books. The supplemental content items accessible via the supplement content options may also depend on the preferences of the readers.

Abstract: Disclosed are various embodiments for item categorizer. The item categorizer is configured to parse, in at least one computing device, at least a plurality of product descriptions of a like item category for identifying a plurality of keywords with regard to the like item category. Furthermore, the item categorizer selects a plurality of subsets of keywords from the plurality of keywords, each subset of keywords comprises a unique combination of the plurality of keywords with respect to each other. Moreover, the item categorizer is configured to generate a respective rule for each corresponding subset of keywords, wherein an application of each respective rule specifies a respective binary result depending upon whether the corresponding subset of keywords is included in a seller product description.