Dynamic Ad Targeting Expansion via Affinity Scores

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In personalized digital media, advertisers often lack sufficient user information, leading to irrelevant advertisements being presented to users who do not match the intended demographic, resulting in missed opportunities for relevant ad placement.

Innovation Solution

An online system maintains user profiles and infers user characteristics through interactions and connections, allowing it to select and present advertisements that match specific targeting criteria, and dynamically expands the target audience based on affinity and performance metrics to ensure relevant ad delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If advertisers use traditional demographic-based targeting, then advertisements can be presented to typical consumers of media, but atypical consumers encounter irrelevant advertisements and advertisers miss opportunities to reach relevant users

Engineering Contradiction:

Improveadvertising targeting accuracyVSAvoiduser information completeness

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent replaces traditional demographic-based mechanical targeting systems with an affinity-based system that uses machine learning models to calculate affinity scores between users and advertisements. This substitution enables more accurate targeting by measuring actual user-ad interaction patterns rather than relying on predefined demographic categories

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements feedback mechanisms by monitoring user interactions with advertisements and using this data to refine affinity calculations. The affinity scores are dynamically updated based on observed user behavior, creating a closed-loop system that continuously improves targeting accuracy while adapting to changing user preferences

Inventive Principle:

Principle #23Feedback

2Productivity

If advertisers strictly follow initial targeting criteria, then ad relevance to specified demographics is maintained, but the target audience is limited and ad performance goals may not be achieved

Engineering Contradiction:

Improveadvertisement performanceVSAvoidtarget audience reach

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent introduces dynamic audience expansion by allowing the target audience to grow beyond initial criteria based on real-time affinity measurements. The system dynamically adjusts the boundary between target and non-target users by incorporating users who demonstrate high affinity through their interactions, even if they don't initially match demographic criteria

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter for audience inclusion from binary demographic matching to a continuous affinity score. By transforming the targeting parameter from categorical (match/don't match) to continuous (affinity score), the system can inclusively target users based on measured engagement likelihood rather than rigid demographic boundaries

Inventive Principle:

Principle #35Parameter changes

3Quantity of substance

If the system expands target audience beyond initial criteria, then more users are reached including those with affinity for the ad, but the precision of targeting may be reduced

Engineering Contradiction:

Improvenumber of users reachedVSAvoidtargeting criterion match accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent applies local quality by maintaining high precision within the core target audience defined by initial criteria while allowing controlled expansion to peripheral users with high affinity scores. Each user segment (core target vs. expanded audience) receives differentiated treatment based on their affinity measurement, preserving precision where needed while expanding reach where appropriate

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS10318983B2Expansion of targeting criteria based on advertisement performance

Publication Date: 2019.06.11 META PLATFORMS INC

AI summary

An online system selects advertisements for presentation a user based on characteristics of the user. The online system monitors performance of advertisements based on a goal for the advertisement and a time interval for achieving the goal. During a time period within the time interval, the online system determines an actual performance of the advertisement and compares the actual performance to a portion of the goal associated with the time period. If the actual performance does not satisfy the portion of the goal associated with the time period, the online system expands targeting criteria of the advertisement to increase a number of users eligible to be presented with the advertisement.