Traffic Quality Scoring With Multi-Factor Session Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing click and impression fraud detection systems classify clicks and impressions in a binary manner, failing to accurately assess the quality of traffic, and do not allow advertisers to set thresholds based on their specific needs, leading to unfair characterization and increased advertising expenses.
Innovation Solution
A software and hardware facility that applies a multi-factor analysis through a rule set to session data, generating a relative score for agent actions, distinguishing between desirable and non-desirable traffic based on factors like physical location, browsing habits, and search terms, allowing for variable pricing and targeted advertising strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If binary classification systems are used to detect click or impression fraud, then the detection process is simple and fast, but the accuracy of traffic quality assessment is poor and advertisers cannot set customized thresholds
Solution Approach 1:
The patent segments the binary classification problem into multiple granular factors (click velocity, time on site, bounce rate, geographic location, device characteristics, etc.). Each factor is evaluated separately and then aggregated to form an overall traffic quality score, allowing for more nuanced and accurate assessment while maintaining operational feasibility through automated multi-factor analysis.
Solution Approach 2:
The system dynamically adjusts traffic quality thresholds based on advertiser-specific requirements and campaign contexts. Rather than using fixed binary classifications, the system allows advertisers to customize quality thresholds and dynamically adapts scoring parameters based on real-time performance data and fraud patterns, enabling both operational efficiency and high measurement precision.
2Ease of manufacture
If binary fraud detection systems are used, then implementation is straightforward, but advertisers are unfairly charged for borderline cases and cannot control traffic quality standards
Solution Approach 1:
The patent transforms the binary quality assessment into a multi-dimensional parameter system where traffic is evaluated on multiple continuous parameters (click velocity, session duration, bounce rate, geographic distribution, device fingerprints). Advertisers can set customized threshold parameters for each factor, allowing flexible control over traffic quality standards while ensuring fair charging decisions based on comprehensive rather than binary evaluation.
Solution Approach 2:
The system implements feedback mechanisms where traffic quality scores and fraud detection results are continuously monitored and used to adjust future classification decisions. Advertiser charging decisions are based on aggregated performance data and feedback loops that refine threshold settings over time, improving fairness and reliability while maintaining implementation feasibility through automated learning and adaptation.
3Measurement precision
If multi-factor analysis with rule sets is applied to score traffic quality, then traffic quality assessment accuracy improves and advertisers can set customized thresholds, but the system complexity increases
Solution Approach 1:
The patent creates a universal multi-factor scoring framework that can be applied across different advertisers, campaigns, and fraud scenarios. The same core rule set and evaluation parameters serve multiple functions: detecting fraud, assessing traffic quality, determining advertiser charging eligibility, and providing actionable insights. This universal system reduces overall complexity by avoiding the need for separate specialized systems for each function.
Solution Approach 2:
The system implements self-service capabilities where advertisers can independently configure their own quality thresholds, review traffic quality scores, and adjust parameters based on their specific needs without requiring complex manual configuration or external intervention. The automated multi-factor analysis performs its own optimization and adaptation, reducing the operational complexity burden on users while maintaining high measurement precision.
Data Source
AI summary
A software and/or hardware facility for scoring the quality of traffic to a site accessible via the Internet or other network. The facility extracts data from one or more data logs that are obtained 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. Lower scores are indicative of traffic having little value, whereas higher scores are indicative of traffic having greater value. The score may be provided to an advertising network and used to charge a variable amount for advertisements based on the quality of traffic that the advertisements receive.