Dynamic OTT Endemic Banners Using Content Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Personalization of endemic media on Over-the-Top (OTT) devices is challenging, as existing ad servers fail to deliver the most accurate, content-based creative that users are likely to take action on, due to limitations in targeting and selection methods.
Innovation Solution
Implementing a content recommendation system to power publisher channels, enhancing ad creativity by presenting Machine Learning (ML) personalized in-channel content in endemic banners, which are dynamically generated based on user preferences and campaign goals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If traditional ad servers use targeting attributes and pre-created creatives, then campaign selection is simplified, but the accuracy of content-based creative delivery deteriorates
Solution Approach 1:
The system transitions from static pre-created creatives to dynamic creative generation. The ad server dynamically generates creatives by combining campaign templates with user-specific content recommendations from the recommendation system, allowing real-time adaptation to user preferences while maintaining campaign goals.
Solution Approach 2:
The recommendation system acts as an intermediary between the ad server and user content delivery. It receives campaign parameters from the ad server, processes user profile data, and returns personalized content recommendations that are then integrated into creatives by the ad server.
2Device complexity
If ad servers select from pre-created creatives, then production complexity is reduced, but the relevance of content to user interests deteriorates
Solution Approach 1:
The creative generation process is segmented into independent components: campaign templates, content recommendations, and creative assembly. This allows the system to maintain simple template structures while achieving high relevance through dynamic content insertion based on user preferences.
Solution Approach 2:
The system changes parameters of the creative delivery process by moving from fixed pre-created creatives to parameter-driven dynamic generation. Content recommendations serve as variable parameters that are injected into templates based on user profiles, enabling high relevance without requiring complex creative production for each scenario.
3Device complexity
If traditional targeting methods are used, then system simplicity is maintained, but user engagement with ads deteriorates
Solution Approach 1:
The recommendation system performs self-service by automatically analyzing user viewing history, preferences, and behavior patterns to generate personalized content recommendations. This eliminates the need for complex manual targeting configurations while significantly improving ad relevance and user engagement.
Solution Approach 2:
The system implements feedback loops where user interaction data (viewing history, preferences, engagement metrics) is continuously fed back into the recommendation system to refine future recommendations. This feedback mechanism enables the system to adapt to changing user interests automatically, improving engagement without increasing operational complexity.
Data Source
AI summary
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content recommendation system powering a streaming media publisher channel to enhance an ad creative being shown to the user via awareness or performance campaigns. This method allows the platform to present the most relevant Machine Language (ML) personalized in-channel content to the publisher platform users in endemic banners that run on the platform which then correspondingly helps drive user reach. An example embodiment operates by implementing personalized content banners that may act as a hook for channel users opening their streaming device, both active and lapsed, to enter back into the channel.