Abstract:
The present teaching relates to managing online experiments. In one example, a plurality of experiment layers is created with respect to a plurality of online users. Each experiment layer includes at least one experiment each of which includes one or more buckets associated with respective features to be experimented on. Each of the plurality of online users is assigned to a corresponding bucket in each experiment layer, such that the user is simultaneously associated with multiple experiments in different layers. User event data related to the plurality of experiment layers are collected from the plurality of online users. One or more contaminated buckets are automatically detected based on the user event data.
Abstract:
A server system may include at least one non-transitory, processor-readable storage medium and at least one processor in communication with the at least one storage medium. The at least one storage medium may include at least one set of instructions for generating a value added in-stream contents (VAC) database for ad display. The at least one processor may be configured to execute the at least one set of instructions to receive an candidate article for display in a stream on a website; determine a sentiment of the candidate article towards a first subject matter associated with the article; classify the candidate article to a first type category based on the sentiment when the sentiment has a positive effect to a commercial success of a second subject matter; and generating a VAC database based on the first type category.
Abstract:
As provided herein, a primary content provider (e.g., a book retailer) may present a campaign for a product (e.g., a novel), comprising non-published content and a keyword (e.g., the novel title), to a permitted content provider (e.g., the publisher of the novel). The permitted content provider may be presented with an option to bid on the keyword. Responsive to the bid being accepted by the primary content provider, a cumulative bid is determined based upon an accumulation of an existing bid from the primary content provider and the bid. The non-published content, but not second non-published content of a second primary content provider, may be selected to be provided to a user based upon the cumulative bid exceeding a second bid for the keyword by the second primary content provider. In this way, content that may be relevant to the user may be identified and provided to the user.
Abstract:
One or more systems and/or techniques for generating a combined advertisement are described herein. A primary advertisement associated with a primary advertiser may be accessed. A primary attribute for the primary advertisement may be defined (e.g., a car advertisement may target teenage boys). A first spot advertisement associated with a first advertiser may be selected based upon the primary attribute of the primary advertisement (e.g., a car tuning advertisement that also targets teenage boys). A combined advertisement may be generated based upon the first spot advertisement and the primary advertisement. In an example, the combined advertisement may be displayed to a consumer based upon a determination that the consumer corresponds to the primary attribute (e.g., a teenage boy visiting a website). In this way, multiple advertisements (e.g., having similar attributes/goals) may be provided through a single combined advertisement.
Abstract:
Disclosed is a system and method for providing automated micro-targeted advertisements to a small group of engaged users based on the users' interactions with each other. The systems and methods disclosed provide relevant advertisements to members of a small targeted online group, where the members of the group share common interests, behaviors, preferences, online activities, and the like. The advertisements include calls to action for a receiving user to consummate a transaction, which encourages product (or brand) engagement by specifically identifying friends (or other users who have an established relationship with the user) that may be interested in a product, thereby, providing an initial dialogue between the friends over the targeted product.
Abstract:
Software on a content-aggregation website obtains a resource associated with a podcast from a website publishing the podcast and stores it e resource on the content-aggregation website. The software adds the resource as a leaf node to a taxonomy generated by the content-aggregation website. The addition is based on data associated with the podcast. The non-leaf nodes in the taxonomy are categories of content. The software determines that a user of the content-aggregation website is qualified as to at least one category that includes the resource as a leaf node. The determination is based at least in part on feedback from the user that includes a viewing or listening history for the user. Then the software serves the resource to the user in a content stream published by the content-aggregation website, based at least in part on a personalization score associated with the resource.
Abstract:
As provided herein, a primary content provider (e.g., a book retailer) may present a campaign for a product (e.g., a novel), comprising non-published content and a keyword (e.g., the novel title), to a permitted content provider (e.g., the publisher of the novel). The permitted content provider may be presented with an option to bid on the keyword. Responsive to the bid being accepted by the primary content provider, a cumulative bid is determined based upon an accumulation of an existing bid from the primary content provider and the bid. The non-published content, but not second non-published content of a second primary content provider, may be selected to be provided to a user based upon the cumulative bid exceeding a second bid for the keyword by the second primary content provider. In this way, content that may be relevant to the user may be identified and provided to the user.
Abstract:
Software on a content-aggregation website obtains a resource associated with a podcast from a website publishing the podcast and stores it e resource on the content-aggregation website. The software adds the resource as a leaf node to a taxonomy generated by the content-aggregation website. The addition is based on data associated with the podcast. The non-leaf nodes in the taxonomy are categories of content. The software determines that a user of the content aggregation website is qualified as to at least one category that includes the resource as a leaf node. The determination is based at least in part on feedback from the user that includes a viewing or listening history for the user. Then the software serves the resource to the user in a content stream published by the content-aggregation website, based at least in part on a personalization score associated with the resource.
Abstract:
In one embodiment, a group of two or more individuals may be identified. A group profile associated with the group of two or more individuals may be obtained. One or more content items and/or one or more advertisements suitable for presenting to the group of two or more individuals may be identified based, at least in part, upon the group profile. The one or more content items and/or one or more advertisements may be provided for access by the group of two or more individuals.