Hardware Event Correlation for Detecting Advertising Fraud
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods are ineffective in detecting bot fraud and other deceptive behaviors in online advertisements, as programmers can easily simulate human interactions, diverting advertising budgets from legitimate publishers.
Innovation Solution
A method and system that detect fraudulent activity by correlating user input hardware events with website interactions, determining fraudulent behavior based on the correlation, and inhibiting ad content transmission when fraudulent activity is detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional ad fraud detection methods are used, then the system remains simple to implement, but it cannot effectively detect bot fraud and simulated human interactions
Solution Approach 1:
The system segments the detection process into distinct components: hardware event collection (mouse, keyboard, touchscreen events), website interaction tracking (page views, ad impressions, clicks), and correlation analysis modules. This segmentation allows each component to specialize in specific data types while working together to detect fraud patterns that would be impossible to capture with a single simple method.
Solution Approach 2:
The patent introduces hardware event data as an intermediary element that bridges the gap between physical user actions and digital website interactions. By collecting and correlating hardware events with ad interactions, the system creates a verification layer that reveals whether interactions are truly human-generated or bot-simulated, solving the detection effectiveness problem without requiring overly complex analysis of individual interaction patterns.
2Measurement precision
If the system correlates hardware events with website interactions to detect fraud, then fraud detection accuracy improves, but data processing complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary actions by pre-defining correlation criteria and thresholds for hardware event matching. Instead of performing complex real-time analysis of every interaction, the system pre-establishes the framework for what constitutes legitimate hardware-interaction correlation, allowing fraud detection to proceed through simpler matching operations during actual ad delivery.
Solution Approach 2:
The correlation analysis provides feedback about the authenticity of user interactions, which then feeds back into ad delivery decisions. When hardware events fail to correlate with website interactions beyond established thresholds, the system identifies this as fraudulent behavior and adjusts ad delivery accordingly, creating a closed-loop system that improves precision while managing processing complexity through targeted analysis rather than exhaustive examination.
3Reliability
If the system inhibits ad content transmission when fraudulent activity is detected, then advertising budget protection improves, but legitimate ad delivery may be blocked
Solution Approach 1:
The system applies local quality by analyzing and evaluating specific ad interactions individually based on their corresponding hardware events, rather than applying a blanket block to all ads or all traffic from certain sources. This localized evaluation allows the system to protect against fraud in specific instances while maintaining normal ad delivery for legitimate users, balancing protection with efficiency through granular, case-by-case assessment.
Data Source
AI summary
Mechanisms for detecting fraudulent activity based on hardware events are provided. In accordance with some embodiments of the disclosed subject matter, the method comprises: receiving a request for advertising content to be placed on a website; receiving data describing physical activity at one or more user input hardware devices; receiving data describing interactions with the website; correlating the data describing interactions with the website with the data describing physical activity at one or more user input hardware devices; determining whether at least a portion of the interactions with the website are indicative of fraudulent behavior based on the correlation; and responding to the request for advertising content on the website by inhibiting the advertising content to be transmitted to the website in response to the determination that at least a portion of the interactions with the website indicates fraudulent behavior.