Viewer Modeling for Guaranteed Ad Reach
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current online advertising systems lack the ability to guarantee reach and pricing for online advertising campaigns in advance, relying on historical GRP calculations after campaign completion, and fail to effectively target specific demographic segments in real-time bidding environments.
Innovation Solution
The system characterizes polarized websites and viewers based on demographic characteristics, predicts GRPs, and prices campaigns accordingly, using a truth set of viewers with known characteristics to establish polarization profiles for both websites and viewers, enabling real-time targeting and guaranteed reach through GRP predictions and pricing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If historical GRP calculations are used after campaign completion, then measurement of audience reach is achieved, but real-time targeting and advance pricing are not possible
Solution Approach 1:
The system performs preliminary actions by characterizing websites and viewers, and predicting GRPs before the advertising campaign begins. This allows advance pricing and real-time targeting capability while maintaining measurement accuracy through the prediction model that is validated against historical data.
2Speed
If real-time bidding is implemented, then ad delivery speed is improved, but ability to guarantee reach and pricing in advance is lost
Solution Approach 1:
The system uses feedback from the GRP prediction model to adjust bidding strategies in real-time while maintaining advance pricing commitments. The model continuously learns from campaign performance data to improve prediction accuracy, ensuring that real-time bidding decisions align with guaranteed reach objectives.
3Measurement precision
If demographic targeting is enhanced, then ad delivery accuracy to specific segments is improved, but system complexity increases
Solution Approach 1:
The system segments the audience into distinct demographic groups and characterizes websites based on their viewer demographics. By breaking down the target audience into manageable segments and assigning probability scores for segment membership, the system achieves precise demographic targeting without overwhelming complexity in the bidding mechanism.
Data Source
AI summary
Systems and methods are disclosed for employing supervised machine learning methods with activities and attributes of viewers with truth as input, to produce models that are utilized in determining probabilities that an unknown viewer belongs to one or more demographic segment categories. Using these models for processing viewer behavior, over a period of time a database of known categorized viewers is established, each categorized viewer having a probability of belonging to one or more segment categories. These probabilities are then used in bidding for online advertisements in response to impression opportunities offered in online media auctions. The probabilities are also used in predicting on-target impressions and GRPs (Gross Rating Points) in advance of online advertising media campaigns, and pricing those campaigns to advertiser/clients. Strategies are also disclosed for fulfilling a campaign when an available inventory of known categorized viewers is not adequate to fulfill a campaign in a required runtime.