Contextual Video Ad Serving with Dynamic Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In guaranteed display advertising systems, serving contextually relevant video advertisements is challenging due to the constant publication of new content and limited video ad inventory, which can lead to under-delivery risks in guaranteed advertisement campaigns, affecting user engagement and revenue metrics like CPCV and CTR.
Innovation Solution
The system employs an evolutionary approach by calculating a similarity score between video content and advertisements using metadata and visual features extracted through Deep Convolutional Neural Networks, ensuring contextually relevant ads are served while providing alternative ads to minimize under-delivery risks if relevant ones are not available.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the publisher serves only closely related video advertisements to content, then user engagement is improved, but there is a risk of under-delivery of advertisements in guaranteed campaigns
Solution Approach 1:
The system dynamically adjusts advertisement selection based on availability of contextually relevant ads. When relevant ads are available, it prioritizes them for user engagement; when not available, it switches to alternative selection methods to ensure guaranteed delivery obligations are met.
Solution Approach 2:
The system changes the selection parameter from strict contextual relevance to a balanced approach considering both relevance and delivery guarantees. It uses similarity scoring to determine when to relax relevance requirements while maintaining acceptable user experience.
2Reliability
If the publisher serves contextually relevant video advertisements, then user engagement and revenue metrics are improved, but the complexity of the advertisement selection system increases
Solution Approach 1:
The system performs preliminary actions by pre-calculating similarity scores between advertisements and content categories, and pre-identifying contextually relevant ads before the actual serving decision is made. This reduces real-time computational complexity while maintaining engagement quality.
Solution Approach 2:
The system introduces an intermediary similarity scoring mechanism that bridges the gap between strict contextual matching and flexible alternative selection. This intermediary layer simplifies the decision-making process by providing a quantitative measure of contextual relevance.
3Productivity
If the publisher prioritizes guaranteed advertisement delivery, then under-delivery risk is minimized, but user engagement and revenue metrics may deteriorate
Solution Approach 1:
The system changes the selection parameter from strict contextual relevance to a balanced approach considering both relevance and delivery guarantees. It uses similarity scoring to determine when to relax relevance requirements while maintaining acceptable user experience.
Solution Approach 2:
The system dynamically adjusts advertisement selection based on availability of contextually relevant ads. When relevant ads are available, it prioritizes them for user engagement; when not available, it switches to alternative selection methods to ensure guaranteed delivery obligations are met.
Data Source
AI summary
The technologies described herein serve contextually relevant advertisements under a guaranteed advertisement campaign. A publisher retrieves a guaranteed advertisement campaign related to a webpage available for serving an advertisement, and identifies a set of advertisements relating to the guaranteed advertisement campaign. Advertisement selecting circuitry of the publisher determines whether an advertisement that is contextually relevant to content published at the webpage is present in the set of advertisements. If there is no contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects an alternative advertisement from the set of advertisements that minimizes an under-delivery risk related to the guaranteed advertisement campaign. If there is a contextually relevant advertisement in the set of advertisements, the advertisement selecting circuitry selects the contextually relevant advertisement. Then, the publisher provides the selected advertisement to a client device.