Network Traffic Quality Scoring System for Fraud Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing systems for assessing the value of traffic associated with network sites are hindered by click fraud and impression fraud, which lead to increased advertising expenses for advertisers and lower perceived value of traffic for publishers.
Innovation Solution
A method and system for scoring the quality of traffic to network sites, which involves extracting session data from server logs, applying a multi-factor analysis using a rule set, and generating non-binary scores based on desirable agent actions, while also preserving score consistency over time and across clients.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If traditional cost-per-click or cost-per-impression systems are used to charge advertisers, then publishers can generate revenue from traffic, but advertisers suffer financial losses due to click fraud and impression fraud
Solution Approach 1:
The system performs preliminary analysis of traffic patterns, user behavior, and session data before charging advertisers. By pre-identifying fraudulent traffic through multi-factor analysis and rule sets, the system prevents payment for invalid clicks or impressions, resolving the contradiction between generating revenue and avoiding fraud losses
Solution Approach 2:
The patent introduces an intermediary traffic quality assessment system between publishers and advertisers. This intermediary analyzes traffic data, applies scoring rules, and determines valid impressions or clicks before billing occurs, protecting both parties from fraud while maintaining the revenue model
2Productivity
If publishers display more advertisements to increase revenue, then advertising income increases, but the perceived value of traffic decreases due to higher fraud rates
Solution Approach 1:
The system implements feedback loops where traffic quality scores from multi-factor analysis are continuously fed back into the advertising delivery and billing process. This feedback mechanism allows publishers to maintain high revenue by identifying and promoting high-quality traffic sources while filtering out fraudulent traffic, thus preserving traffic value assessment accuracy
Solution Approach 2:
The patent changes the parameters of traffic assessment from simple click/impression counts to multi-dimensional quality scores incorporating user behavior, session duration, device information, and pattern analysis. This parameter transformation enables precise differentiation between fraudulent and valuable traffic even as volume increases
3Quantity of substance
If advertisers increase spending on advertising to maintain visibility, then ad exposure increases, but the return on investment decreases due to fraudulent clicks and impressions
Solution Approach 1:
The system performs preliminary validation of traffic quality before advertisers pay for exposure. By pre-identifying and filtering fraudulent traffic through behavioral analysis and rule-based scoring, the system ensures that advertising spend is directed only toward valid, high-quality impressions and clicks, maintaining ROI while preserving exposure quantity
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 may generate training set data and use the training set data to identify parameters indicative of fraudulent traffic to a site and reduce the effect of fraudulent traffic advertisers and publishers. The facility may score the quality of traffic and determine combinations of parameters that are indicative of the quality of traffic to the site. Traffic to the site may be scored based on the combination of parameters associated with the one or more sessions. Lower scores are indicative of traffic having little value to a publisher, advertiser, or third party; higher scores are indicative of traffic having greater value.