Vishal Goenka

Embodiments of a system method and computer program product for selecting an advertisement and presenting it to a user are described. Products and services offered by various merchants are read using a merchant specific catalog and stored in a common format. Categories for such products and services are normalized and virtual categories are created using various product attributes. Visual creatives, termed as ad-templates are created to control the visual and interactive aspects of the ad… Show more

Embodiments of a system method and computer program product for selecting an advertisement and presenting it to a user are described. Products and services offered by various merchants are read using a merchant specific catalog and stored in a common format. Categories for such products and services are normalized and virtual categories are created using various product attributes. Visual creatives, termed as ad-templates are created to control the visual and interactive aspects of the ad, including ad-size, color, as well as product attributes that are displayed in the ad. Ad-templates may be constrained to specific products or product categories. A learning algorithm uses an adaptive sampling process to sample various products, product categories and ad-templates independently for different learning units such as individual users, groups of users determined by some demographics, individual web pages and groups of web pages grouped using various similarity criteria. Show less

A system and a computer-implemented method for sharing online content are provided. The method is implemented using a computer device coupled to a user interface and a memory device. The method includes receiving, from a sharer, a selection of at least one feed of online content to be shared and at least one sharee of the feed of online content, the feed of online content including a plurality of items, each item including a reference identifier linking each item to respective historical… Show more

A system and a computer-implemented method for sharing online content are provided. The method is implemented using a computer device coupled to a user interface and a memory device. The method includes receiving, from a sharer, a selection of at least one feed of online content to be shared and at least one sharee of the feed of online content, the feed of online content including a plurality of items, each item including a reference identifier linking each item to respective historical interaction data, pairing the sharer with at least one sharee of the feed of online content by securely linking an account of the sharer to an account of the sharee, sharing the selected at least one feed of online content from the sharer to the sharee, and displaying a link to the shared feed as a normal feed object under the sharee's account. Show less

Systems, methods, and computer-readable media for representing and processing inter-slot co-occurrence constraints on component selection for dynamically generated content items are disclosed. Components available for constructing the content items are organized into a hierarchy of categories. Co-occurrence constraints are specified in terms of categories in the hierarchy rather than explicit enumerated black-lists or white-lists at the component-to-component level. A set of processing rules… Show more

Systems, methods, and computer-readable media for representing and processing inter-slot co-occurrence constraints on component selection for dynamically generated content items are disclosed. Components available for constructing the content items are organized into a hierarchy of categories. Co-occurrence constraints are specified in terms of categories in the hierarchy rather than explicit enumerated black-lists or white-lists at the component-to-component level. A set of processing rules based on the hierarchical taxonomy are used to expand a set of co-occurrence constraints specified in terms of categories into explicit enumerations of allowed component combinations, and to resolve potential conflicts in the set of co-occurrence constraints in a predictable manner. The explicit enumerations of allowed component combinations can be stored in a relational data table. When constructing a content item, candidate components can be obtained by querying the relational data table. Show less