Abstract: In some embodiments, an apparatus includes a weight module, a performance module and an allocator module. The weight module calculates a weight for each segment from a set of segments of potential advertisement placements matching a criterion. The weight for a segment is based at least partially on (1) a budget score for an advertisement campaign and (2) a number of potential placements for the segment. The performance module calculates a performance score for the advertisement campaign at each segment from the set of segments. The performance score of the segment is based on a success metric for an advertisement at the segment and a number of impressions for the segment. The allocator module presents the advertisement at a placement associated with the segment if the weight for the segment is greater than a first threshold and the performance score for the segment is greater than a second threshold.

Abstract: In one embodiment, a method for optimizing advertisement performance is provided. In one embodiment, advertisements may be clustered together into different buckets of advertisements. Rich media content may also be clustered together. A performance model may then be generated that is based on previous performance of ads with content. The performance data may be used to predict which ads may provide the best performance when shown with a target piece of content that is going to be displayed. Particular embodiments use performance data for advertisements in an ad bucket to determine which ad bucket out of multiple ad buckets may provide the best performance for a content bucket that includes the target content. The ad bucket includes a plurality of ads and the method determines which ad should be displayed with the target content. In one embodiment, performance data is used to determine which ad to display.

Abstract: In one embodiment, content and events are received. The content is analyzed based on to determine a mood score based on events. The mood score is used to classify the content and event with a mood. The mood classification may then be used to affect actions being performed. For example, the mood may affect ad matching to the content. In one example, depending on the mood that is calculated, different ads may be matched to different portions of the content. Accordingly, more effective ads may be served with the content when the mood classification is taken into account.

Abstract: In one embodiment, an advertisement is matched to subject matter in a portion of rich media content, such as a digital video, Flash™ animation, etc. For example, during the playing of rich media content, it may be determined by audio recognition techniques that the content's subject matter matches or correlates with an advertisement. Rendering preferences associated with the advertisement are then determined. The rendering preferences may be used to determine how the advertisement should be rendered (i.e., displayed in association with the content). The advertisement is then served to a device. The advertisement is served such that it can be rendered relative to a time that the portion of media is being displayed on the device.

Abstract: In one embodiment, a statistical pattern recognition engine determines content for a statistical pattern recognition task. The content and/or information related to the content is analyzed to determine a model to use in the statistical pattern recognition. For example, models may be classified in a plurality of domains based on different sets of data used to train models in the domain. The models may be classified based on knowledge sources used to generate the models, such as a news knowledge source, entertainment knowledge source, business knowledge source, etc. A model in the plurality of models is then determined based on the analysis where the determined model is classified in a domain. The model is then used by the statistical pattern recognition engine to perform the statistical pattern recognition task. For example, spoken words are transcribed into text using the determined model.