Dynamic Pricing for Sponsored Content Impressions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for displaying sponsored content in online networks face challenges in balancing budget utilization and revenue generation, often resulting in sponsored content being displayed at zero cost to advertisers due to inefficient pricing mechanisms, which disincentivizes them from sponsoring content.
Innovation Solution
Implementing dynamic pricing for sponsored content impressions based on machine-learned models that predict user interactions and adjust prices in real-time to optimize budget consumption and improve performance metrics, ensuring that advertisers' budgets are utilized effectively throughout the day.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If sponsored content is displayed using traditional pricing mechanisms, then advertisers may spend their budgets quickly, but the content may be displayed at zero cost due to inefficient pricing, reducing revenue generation
Solution Approach 1:
The patent implements dynamic pricing for sponsored content impressions, where the price adjusts in real-time based on machine-learned predictions of user interactions. This dynamic mechanism ensures advertisers' budgets are fully utilized while optimizing revenue generation, resolving the contradiction between budget efficiency and revenue loss
Solution Approach 2:
The system uses machine-learned models that continuously learn from user interaction data to predict and adjust pricing. This feedback loop enables the system to optimize both budget consumption and revenue generation by adapting prices based on actual user behavior patterns
2Adaptability or versatility
If sponsored content is mixed with non-sponsored content in feeds, then visibility and engagement may improve, but coordinating display becomes technically challenging
Solution Approach 1:
The patent changes the parameter of content prioritization by introducing a bidding mechanism where sponsored content can be prioritized based on bid amount. This allows flexible mixing of sponsored and non-sponsored content while simplifying coordination through a clear pricing and prioritization framework
3Productivity
If machine-learned models are used to predict user interactions and adjust prices in real-time, then budget utilization and revenue generation are optimized, but system complexity increases
Solution Approach 1:
The system employs self-service mechanisms where machine-learned models automatically predict user interactions and adjust pricing without manual intervention. This automation optimizes budget utilization and revenue while managing complexity through autonomous decision-making algorithms
Data Source
AI summary
In an example embodiment, a bid of an impression of a piece of content, while dynamically set at impression time, may be based on a base bid that is something of a rough indicator of what the estimated price will be. That base bid then is adjusted dynamically up or down at impression time. This base bid can be determined by dividing the expected number of impressions for a day by a total daily budget. The expected number of impressions may be determined by using the empirical number of impressions from the previous day. As such, in an example embodiment, the prediction of the number of impressions for a day utilizes a corrected version of the empirical number of impressions from the prior day, with the corrected version based on a specialized formula with weights trained by a machine learning algorithm.