Traffic Quality Scoring Using Multi-Factor Session Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing click and impression fraud detection systems classify clicks or impressions in a binary manner, failing to accurately assess the quality of traffic, and do not allow advertisers to set thresholds for the type of traffic they are willing to pay for, leading to unfair characterization and increased advertising expenses.
Innovation Solution
A software and hardware facility that applies a multi-factor analysis using a rule set to session data from server logs, identifying desirable agent actions and generating a relative score for each action, allowing for variable pricing based on traffic quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If binary classification systems are used to detect click or impression fraud, then the detection process is simple and fast, but the measurement precision of traffic quality is insufficient and cannot accurately distinguish between good and bad traffic
Solution Approach 1:
The patent transforms the binary classification approach into a multi-parameter scoring system that evaluates multiple attributes of clicks and impressions (such as user behavior patterns, device characteristics, temporal patterns, and engagement metrics) to generate continuous quality scores. This allows for more nuanced traffic quality assessment while maintaining computational efficiency through structured parameter evaluation.
Solution Approach 2:
The detection system is segmented into multiple independent evaluation modules, each assessing specific aspects of traffic quality (click validity, impression authenticity, user engagement, etc.). These modular segments can be independently optimized and combined to achieve high measurement precision without requiring a monolithic complex system.
2Adaptability or versatility
If binary fraud detection systems are used, then the system is easy to operate, but advertisers cannot set thresholds for the type of traffic they are willing to pay for
Solution Approach 1:
The system implements dynamic threshold settings that allow advertisers to adjust their traffic quality requirements based on campaign objectives, budget constraints, and performance targets. The scoring system generates continuous values that can be filtered at multiple levels, providing adaptability while maintaining ease of operation through standardized interfaces and automated recommendations.
Solution Approach 2:
The patent creates a universal scoring framework that serves multiple functions: fraud detection, traffic quality assessment, pricing optimization, and campaign performance analysis. This multi-functional system accommodates diverse advertiser needs through configurable parameters while maintaining a unified operational interface.
3Loss of information
If binary classification is applied to all clicks and impressions, then the processing is efficient, but the loss of information occurs because nuanced traffic quality differences are not captured
Solution Approach 1:
The patent replaces the mechanical binary classification mechanism with an information-rich scoring system that uses weighted parameter evaluation and probabilistic modeling. This substitution captures nuanced traffic quality differences through continuous score values while maintaining processing efficiency through algorithmic optimization and streamlined data pipelines.
Solution Approach 2:
The system transitions from one-dimensional binary classification to multi-dimensional continuous scoring by introducing additional evaluation dimensions (user engagement metrics, device fingerprints, temporal patterns, geographic distribution). This dimensional expansion captures information nuances without proportionally increasing processing complexity through efficient multidimensional data structures.
Data Source
AI summary
Disclosed software and/or hardware score the quality of traffic to a site accessible via the Internet or other network. The facility extracts data from data logs from a publisher, advertiser, or third party. A multi-factor analysis in the form of a rule set is applied by the facility to the data. The analysis of the data identifies agent actions that are desirable to a publisher, advertiser, or third party. The facility generates a relative score for each agent action. The score may be used to assess the quality of traffic received by a network site. In some embodiments, lower scores are indicative of traffic having little value and higher scores are indicative of traffic having greater value. In some embodiments, lower scores indicate higher value. Some embodiments provide the scoring to an advertising network in order to charge a variable amount for advertisements based on the quality of traffic received.