Ad Impression Viewability Scoring for Fraudulent Traffic Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advertisers face challenges in controlling and managing the distribution of advertisements due to fraud activities such as click fraud, impression fraud, and deceptive behaviors, including botnet traffic, iframe stuffing, and ad stacking, which affect the effectiveness and cost of their advertising campaigns.
Innovation Solution
A method and system for detecting suspicious activity in advertisement impressions by analyzing viewability statistics, browser spoofing rates, and page popularity using a hardware processor, and employing machine learning to identify fraudulent websites and domains.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If advertisement distribution is expanded to reach target audience, then advertising effectiveness is improved, but exposure to fraud activities increases
Solution Approach 1:
The system performs preliminary detection of fraud indicators before advertisements are served. By analyzing webpage characteristics, domain reputation, and historical fraud data in advance, the system identifies suspicious websites and prevents fraudulent ad impressions from occurring, thereby protecting advertising effectiveness while expanding distribution
Solution Approach 2:
The patent introduces an intermediary detection layer between the advertisement distribution system and the target audience. This intermediary system analyzes multiple indicators (webpage content, domain reputation, historical fraud patterns) to filter out fraudulent sites, allowing legitimate advertisements to reach users while blocking fraud attempts
2Reliability
If fraud detection mechanisms are implemented, then advertising integrity is improved, but system complexity increases
Solution Approach 1:
The fraud detection system is segmented into multiple independent analysis modules, each evaluating specific indicators (domain reputation, webpage content, historical fraud data, user behavior patterns). These modular components can be independently developed, maintained, and scaled, reducing overall system complexity while maintaining high advertising integrity
Solution Approach 2:
The system dynamically adjusts detection parameters and thresholds based on learned fraud patterns and historical data. By changing parameters such as fraud score thresholds, weighting of different indicators, and detection sensitivity, the system adapts to evolving fraud techniques without requiring fundamental architectural changes, thus managing complexity
3Measurement precision
If multiple advertisement indicators are analyzed, then fraud detection accuracy is improved, but data processing time increases
Solution Approach 1:
The system pre-calculates and stores key indicators such as domain reputation scores, historical fraud patterns, and webpage characteristics before they are needed for detection. This preliminary preparation of data allows the system to perform accurate multi-indicator analysis in real-time without excessive processing delays during actual ad serving
Solution Approach 2:
The detection system applies different levels of analysis depth to different indicators based on their reliability and computational cost. High-value, low-cost indicators (such as domain reputation) are analyzed in detail, while less critical indicators receive lighter analysis, optimizing the balance between detection accuracy and processing time
Data Source
AI summary
Systems, methods, and media for detecting suspicious activity in connection with advertisement impressions are provided. In some embodiments, the method includes: collecting advertisement impression information associated with a plurality of pages; determining, from the collected advertisement impression information, an indication of whether a browser application detected that an advertisement displayed on a webpage was viewable in a browser window; determining, from the collected advertisement impression information, a plurality of viewability statistics for each of the plurality of pages, wherein each viewability statistic indicates a likelihood of whether an advertisement displayed on a webpage was viewable in a browser window; comparing the plurality of viewability statistics with the indication from the browser application; determining a viewability score for the advertisement impression based on the comparison; and identifying the advertisement impression as likely to be suspicious based on the determined viewability score.