Messaging App Ad Scoring via Compatibility Subsidies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertisement systems that include links to messaging applications are costly and impractical, often requiring human moderators or difficult-to-train bots for user engagement, while raising privacy concerns for users due to data monitoring.
Innovation Solution
An online system determines a compatibility score between users and advertisements based on criteria such as user characteristics, historical interactions, and purchasing habits, adjusting bid prices with subsidies to prioritize ads likely to result in deep conversations, ensuring user privacy through encrypted messaging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If human moderators are used to monitor advertiser accounts for live chat with users, then user engagement quality is improved, but operational cost and device complexity increase
Solution Approach 1:
The system enables automated self-service through machine learning models that automatically determine compatibility scores and select advertisements, eliminating the need for human moderators to manually monitor and match users with ads. The algorithm independently performs the engagement quality function that previously required human intervention.
Solution Approach 2:
The patent replaces the mechanical human moderation system with an automated computational system using machine learning algorithms. The system substitutes human cognitive processes with algorithmic calculations that assess compatibility between users and advertisements based on multiple criteria, thereby reducing operational complexity while maintaining engagement quality.
2Productivity
If computerized bots are used to monitor advertiser accounts, then operational cost is reduced, but engagement effectiveness deteriorates due to difficulty in training
Solution Approach 1:
The system changes the parameters of bot operation by using machine learning models that continuously learn from data to determine compatibility scores. Instead of relying on pre-programmed or manually trained bots, the system dynamically adjusts its decision-making parameters based on analyzed criteria such as user characteristics, advertiser characteristics, and historical interaction data, thereby improving engagement effectiveness while maintaining operational efficiency.
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously improves its compatibility assessments based on outcomes from previous ad selections and user interactions. This feedback loop enables the bot to learn and adapt over time, resolving the training difficulty issue while maintaining high operational efficiency.
3Productivity
If the online system monitors communication between user and advertiser to gather data, then advertising effectiveness is improved, but user privacy is compromised
Solution Approach 1:
The system extracts and analyzes only the necessary minimal data elements required for determining compatibility scores, such as user characteristics and advertiser characteristics, without monitoring or storing the actual communication content. This extraction approach enables advertising effectiveness through data analysis while protecting user privacy by leaving sensitive communication details untouched and private.
Solution Approach 2:
The system applies different quality levels of data processing to different aspects of the advertising system. It uses detailed analysis of user and advertiser characteristics for compatibility assessment, but applies no monitoring or analysis to the actual communication between user and advertiser. This localized approach to data quality enables effective advertising while maintaining privacy in the communication channel.
4Measurement precision
If compatibility scoring based on multiple criteria is implemented, then ad selection accuracy is improved, but computational complexity increases
Solution Approach 1:
The system segments the compatibility assessment into distinct modular criteria including user characteristics, advertiser characteristics, and historical interaction data. Each criterion can be independently calculated and combined to form the overall compatibility score. This segmentation improves measurement precision by allowing detailed analysis of each factor while managing system complexity through modular, independent computation of each criterion.
Data Source
AI summary
An online system receives a content item from a content provider, the content item having a bid price and including a link to a messaging application. The link is configured to initiate a direct message in the messaging application between the content provider and a user who interacts with the content item. The online system receives a request for content items from a target user and determines a compatibility score between the target user and the content item based on one or more sets of criteria. A first set of criteria indicates a compatibility between the user and the messaging application. The online system determines a subsidy for the content item based on the compatibility score. The online system adjusts the bid price with the determined subsidy to determine an auction price and includes the content item with the auction price in a selection process for presentation to the user of the online system.