Audience Analysis Server for Fraudulent User Attribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately measuring online audience size is challenging due to issues like multiple accounts, device usage from various locations, and nefarious activities such as bot creation and hijacking, which inflate or distort viewer metrics.
Innovation Solution
An audience analysis server processes online transactions to attribute them to specific audience members, analyzing unique identifiers and contextual information to distinguish legitimate from illegitimate behavior, and refine audience measurements by correlating sets and identifying relationships between users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If automated programs create fake user accounts to inflate visitor numbers, then the measured audience size increases, but the accuracy of audience measurement deteriorates
Solution Approach 1:
The patent introduces an audience measurement system that acts as an intermediary between website traffic data and advertising entities. This system uses multiple data sources including device identifiers, browser characteristics, and behavioral patterns to create a intermediary layer of verification that distinguishes legitimate users from bots, thereby maintaining measurement accuracy while still capturing audience size
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring traffic patterns and comparing them against known bot behaviors. When fraudulent activity is detected, the system adjusts its measurement algorithms in real-time to exclude these fake accounts, ensuring that the final audience measurement reflects only legitimate users
2Quantity of substance
If multiple accounts are created by single users for the same website, then the measured unique visitors increase, but the reliability of audience measurement deteriorates
Solution Approach 1:
The patent merges multiple data points including device identifiers, IP addresses, browser characteristics, and user behavioral patterns to create a unified view of each user. By combining these various identifiers and cross-referencing them across multiple sessions and devices, the system can reliably determine when multiple accounts belong to the same individual, thus preventing inflation of unique visitor counts
3Adaptability or versatility
If users access the same website from various personal devices and locations, then the measured audience distribution increases, but the difficulty of detecting and measuring legitimate users increases
Solution Approach 1:
The system segments user identification into multiple independent components including device identifiers, network information, browser characteristics, and behavioral biometrics. By segmenting the identification process into these separate but complementary components, the system can track users across devices and locations while maintaining the ability to verify legitimacy through the collective pattern of these segments
Data Source
AI summary
Online entities oftentimes desire to ascertain information about their audience members. To determine information about audience members and their activities, online transactions including information about transactions performed by audience members are collected. One or more audience analysis processes are applied to the online transactions to determine the collection of online transactions performed by a given audience member. With an accurate assignment of online transaction to the audience member, the audience member and associated transactions may be classified as a legitimate or illegitimate.