Browsing Identity Verification Using Identifier Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online systems face challenges in verifying the authenticity of interactions with client devices, as entities may deceive the system by generating fake traffic and clicks, leading to irregular patterns that are difficult to distinguish from organic user behavior.
Innovation Solution
The online system employs an identifier graph to analyze device interactions, linking client devices with associated browser IDs and session IDs to determine the likelihood of fabricated interactions by calculating the proportion of suspicious to valid interactions, with a threshold-based approach to identify potential manipulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the online system tracks and analyzes device identifiers to verify interaction authenticity, then the ability to detect fabricated interactions is improved, but the system complexity and computational resources required increase
Solution Approach 1:
The system segments the verification process into distinct components: collecting device identifiers from interactions, building an identifier graph with devices as nodes and interactions as edges, analyzing graph patterns to detect anomalies, and making verification decisions. This segmentation allows each component to be optimized independently and reduces overall system complexity.
Solution Approach 2:
The identifier graph serves as an intermediary data structure between raw interaction data and verification decisions. It transforms complex interaction patterns into analyzable graph structures, enabling efficient detection of fabricated interactions without requiring direct complex analysis of raw data.
2Measurement precision
If the system builds and maintains an identifier graph linking devices with browser IDs and session IDs, then the precision in identifying organic versus non-organic interactions is improved, but the data processing time and computational overhead increase
Solution Approach 1:
The system performs preliminary actions by continuously collecting device identifiers and building the identifier graph in the background as interactions occur, rather than analyzing data only when verification is needed. This pre-processing enables faster verification decisions when fabricated interactions need to be detected.
Solution Approach 2:
The identifier graph automatically updates itself as new interactions are recorded, with the system self-managing the graph construction and maintenance without requiring external intervention. This self-service approach reduces processing overhead during verification operations.
3Reliability
If the system analyzes the proportion of suspicious interactions to total interactions using threshold-based detection, then the reliability in determining publisher fabrication is improved, but the difficulty of detecting and measuring subtle manipulation patterns increases
Solution Approach 1:
The system changes the parameter of analysis from individual interaction evaluation to proportion-based analysis, calculating the ratio of suspicious interactions to total interactions. By adjusting the threshold parameter, the system can reliably determine fabrication while adapting to different publication contexts and manipulation patterns.
Solution Approach 2:
The system implements feedback mechanisms where verification results are fed back into the identifier graph analysis, continuously refining the detection model. This feedback loop improves reliability over time by learning from detected patterns and adjusting detection sensitivity accordingly.
Data Source
AI summary
An online system determines the likelihood of an interaction between a user and a content item being an invalid interaction. The online system receives an indication of an interaction of a client device with a content item. The online system identifies a device ID for the client device and determines whether the device ID is associated with one or more browser IDs. If the device ID is not associated with any browser ID, the received interaction is likely an invalid interaction. The online system may further determines the likelihood of an online publisher manufacturing interactions. The online system determines a number of invalid interactions and a number of valid interactions associated with the online publisher. The online system determines a ratio between the number of invalid and valid interactions. If the ratio is larger than a threshold value, the online system determines that the online publisher is likely manufacturing interactions.