Social Network Ad Ranking via Dynamic Conversion Factor

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional social networking systems face challenges in maintaining user interaction with organic content due to the presence of advertisements, which can decrease overall engagement and revenue potential, as they lack effective methods to gauge the impact of advertisements on feed quality and user interaction.

Innovation Solution

The system calculates partial engagement scores for both organic and sponsored content, adjusts parameters to optimize their placement, and uses a conversion factor to balance engagement scores with monetary value, ensuring that advertisements do not disproportionately displace organic content, thereby maintaining feed quality and user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If the social networking system increases the number of advertisements presented to users, then revenue is improved, but user interaction with organic content decreases

Engineering Contradiction:

ImproverevenueVSAvoiduser interaction with organic content

Core Design Contradiction:

Loss of energyVSProductivity

Solution Approach 1:

The system dynamically adjusts the conversion factor parameter that translates bid amounts into ranking score adjustments. This parameter modification allows the system to optimize advertisement placement while maintaining acceptable levels of organic content engagement, resolving the contradiction between revenue maximization and user interaction preservation

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system implements dynamic parameter adjustment where the conversion factor is modified based on real-time or near-real-time performance metrics. This dynamic approach allows the system to adapt advertisement density and placement to maintain user engagement while maximizing revenue, rather than using static advertisement insertion rules

Inventive Principle:

Principle #15Dynamics

2Area of stationary object

If the social networking system boosts the ranking score of sponsored content items, then advertisement visibility is improved, but the overall quality of the feed decreases

Engineering Contradiction:

Improveadvertisement visibilityVSAvoidfeed quality

Core Design Contradiction:

Area of stationary objectVSManufacturing precision

Solution Approach 1:

The system modifies the conversion factor parameter that controls the magnitude of ranking score adjustment for sponsored content. By dynamically adjusting this parameter, the system can control the degree to which advertisements are boosted in the feed, balancing advertisement visibility with maintenance of overall feed quality

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from user interaction metrics to adjust the conversion factor and thereby control the impact of advertisement boosting on feed quality. When user engagement with organic content decreases, the system can reduce the conversion factor to limit advertisement dominance, creating a feedback loop that maintains feed quality

Inventive Principle:

Principle #23Feedback

3Loss of energy

If the social networking system presents advertisements together with organic content, then revenue opportunities are improved, but user attention is divided

Engineering Contradiction:

Improverevenue opportunitiesVSAvoiduser attention

Core Design Contradiction:

Loss of energyVSLoss of information

Solution Approach 1:

The system applies different ranking score adjustments to different sponsored content items based on their bid amounts and relevance. By locally optimizing the conversion factor application to individual advertisements rather than uniformly boosting all ads, the system can maintain user attention while capturing revenue opportunities from high-value, relevant advertisements

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS9922335B2Selecting organic content and advertisements for presentation to social networking system users based on user engagement

Publication Date: 2018.03.20 META PLATFORMS INC

AI summary

A social networking system dynamically adjusts a number of advertisements presented to a user along with organic content items by modifying a ranking including organic content items and advertisements. Partial engagement scores are generated for organic content items based on an expected amount of user interaction with each organic content item, and scores are generated for advertisements based on expected user interaction and bid amounts associated with each organic content item. An engagement score measuring the user's estimated interaction with a content feed including organic content items without advertisements and an additional engagement score measuring the user's estimated interaction with a content feed including organic content items and advertisements are determined from the partial engagement scores and the scores. A difference between the additional engagement score and the engagement score modifies a conversion factor used to combine expected user interaction and bid amounts to generate advertisement scores.