Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: A content server generates an ad review display that allows users to review previously-presented ads. The content server provides a stream of media content to a client device for presentation to a user of the client device, and generates an ordered list comprising ad tiles corresponding to ads presented to the user with the stream of media content. The content server generates an ad review display based on the ordered list. The ad review display comprises one or more ad tiles organized along a first axis of the ad review display according to their position in the ordered list. The content server sends the ad review display to the client device for presentation to the user. Responsive to receiving a request to replay a previously-presented ad from the client device, the content server inserts the ad into the stream of media content being provided to the client device.

Abstract: According to some example embodiments, a method includes calculating learning values associated with a plurality of listings, at least one of said learning values associated with one of said listings representing a value based, at least in part, on a probability distribution of selections of said listing. The method further includes applying said learning values to ranking scores associated with said listings to provide an updated ranking, and electronically auctioning advertising inventory to purchasers associated with said listings based, at least in part, on said updated ranking.

Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: Personalized content is generated from different media items using a content index. The content index is generated or updated by identifying segments of media items that are of particular interest to users. User interactions with the media items are analyzed and metadata of segments of media items that are determined to be of particular interest to the users is recorded. The parameters associated with a request for personalized content for a user are matched with the recorded metadata to identify relevant media items or segments of media items which are transmitted to the user as the personalized content.

Abstract: Techniques are provided, for use in electronic or online advertising, that can be viewed as going beyond geographic proximity, including determination and use of convenience-based metrics in advertisement targeting, pricing, selection and packaging. For example, based on information including an actual or anticipated consumer location and a store location, one or more possible or likely consumer travel routes may be determined. Based at least in part on this, metrics, such as convenience-based metrics, can be determined and used in aspects of electronic or online advertising, such as consumer travel distance, travel time, or number or travel proximity of alternative stores.

Abstract: Techniques are provided relating to optimization of an online advertising campaign. Information is obtained relating to online advertising, associated with a brand associated with an online advertising campaign, directed to each of a set of individuals. Information is also obtained relating to offline behavior of the individuals in association with the brand. One or more metrics are determined that are associated with a relationship between the online advertising and the offline behavior. Optimization of at least one parameter of the online advertising campaign is performed based at least in part on at least one of the one or more metrics.

Abstract: Techniques are provided relating to advertising campaign optimization. Information is obtained relating to online and offline behavior of a set of individuals in association with a brand associated an advertising campaign. Based at least in part on the information, one or more metrics are determined reflecting an association between online advertising and offline behavior relating to the brand, or vice versa. Optimization is performed for at least one parameter of an online advertising campaign or an offline advertising campaign based at least in part on at least one of the one or more metrics. The campaign could also be a combined offline/online campaign.

Abstract: According to some example embodiments, a method includes calculating learning values associated with a plurality of listings, at least one of said learning values associated with one of said listings representing a value based, at least in part, on a probability distribution of selections of said listing. The method further includes applying said learning values to ranking scores associated with said listings to provide an updated ranking, and electronically auctioning advertising inventory to purchasers associated with said listings based, at least in part, on said updated ranking.

Abstract: Some embodiments of the invention provide techniques for placing “placeholder” bids in an auction associated with online advertising marketplace. Placeholder bids can include bids that are not actually entered or placed in the auction or marketplace. Rather, placeholder bids can include hypothetical bids. Impacts of placeholder bids, should the placeholder bids have been entered or placed as actual bids, can be assessed. An assessment can include assessing an impact on auction and marketplace parameters, an impact on bid or campaign performance, and an impact on downstream parameters such as user behavior, such as associated conversions or purchasing.

Abstract: Embodiments are directed towards employing a playful incentive to encourage users to provide feedback that is useable to train a classifier. The classifier being associated with any of a variety of different settings, including but not limited to classifying: messages as ham/spam, images, advertising, bookmarking, music, videos, photographs, shopping, or the like. An animated image, such as a pet, provides an interface to the classifier that encourages and responds to user feedback. Users may share their classifiers or aspects thereof with other users to enable a community of knowledge to be applied to a classification task, while preserving privacy of the user feedback. One form of sharing may be within the context of a competitive game. Various evaluations may be performed on a classifier to indicate user feedback consistency, or quality. Classifiers may also be used to provide users with advertisements, products, or services based on the user's feedback.