Pair Risk Detection for Fraudulent User-Content Provider Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing click fraud detection systems fail to identify fraudulent user-content provider pairs across various attack techniques, including host-based, proxy-based, botnet-based, and coalition-based attacks, as they primarily focus on individual entities rather than the relationship between them.
Innovation Solution
A method and system for identifying fraudulent user-content provider pairs by determining initial risk values, generating functional representations, and converging them to identify a pair risk value, applying a fraudulent label to pairs exceeding a threshold, thereby preventing future monetary gains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional click fraud detection systems focus on individual entities (users or content providers separately), then the detection system is simpler to implement, but it fails to identify fraudulent user-content provider pairs across various attack techniques
Solution Approach 1:
The patent combines separate detection of users and content providers into a unified pair-based detection system. By merging the risk assessment of both entities and analyzing their interaction patterns together, the system achieves more accurate fraud detection across all attack types while managing complexity through structured risk value calculations and convergence mechanisms.
2Measurement precision
If the system analyzes relationships between multiple content providers and user devices using functional representations and convergence, then fraud detection accuracy improves, but computational complexity increases
Solution Approach 1:
The patent implements dynamic risk value calculations where initial risk values are continuously updated through functional representations that capture interaction patterns. The convergence mechanism dynamically adjusts risk assessments based on observed behaviors, allowing the system to adapt to evolving fraud patterns while managing computational load through iterative refinement rather than exhaustive analysis.
Solution Approach 2:
The convergence process incorporates feedback loops where risk values are repeatedly calculated and refined based on interaction data. This feedback mechanism allows the system to progressively improve detection accuracy by learning from observed patterns, with each iteration providing more precise risk assessments until convergence is achieved.
3Reliability
If the system applies fraudulent labels to high-risk pairs in real-time, then prevention effectiveness increases, but processing time for risk assessment must be minimized
Solution Approach 1:
The system performs preliminary risk assessments by calculating initial risk values for users and content providers before actual fraudulent interactions occur. By pre-establishing risk profiles and monitoring patterns, the system can quickly identify and label fraudulent pairs in real-time, reducing the time needed for assessment while maintaining high prevention effectiveness.
Data Source
AI summary
The present teaching generally relates to identifying fraudulent content provider-user device pairs. In one embodiment, an initial user risk value and an initial content provider risk value may be determined. A first functional representation of a user risk value may be generated based on the initial user risk value and relational data. A second functional representation of a content provider risk value may be generated based on the initial content provider risk value and the relational data. A converged user risk value and a converged content provider risk value associated with the first and second representations converging may be determined. A pair risk value may be determined based on the converged user risk value and the converged content provider risk value. A fraudulent label may then be applied to interaction events detected by the content provider from the user in response to the risk pair value satisfying a condition.