Click Quality Anomaly Detection for Invalid Traffic

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current web analytics tools face challenges in detecting invalid clicks, particularly fraudulent clickthroughs, which can inflate advertising costs and undermine the effectiveness of pay-per-click advertising by failing to distinguish between genuine and artificial clicks.

Innovation Solution

The solution involves analyzing historic click quality data to identify anomalies, such as spikes in clicks without corresponding web analytics data, and using metrics like 'click past' to characterize click quality, which helps in flagging potential invalid clicks by measuring the depth and duration of visitor engagement beyond the landing page.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If web analytics tools track all clickthroughs to monitor advertising effectiveness, then the quantity of collected data increases, but the ability to distinguish valid from invalid clicks deteriorates

Engineering Contradiction:
Improvequantity of click dataVSAvoidaccuracy of click validation
Core Design Contradiction:
Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent segments click data into multiple categories based on engagement metrics: clicks that view the landing page, clicks that navigate to additional pages, and clicks that remain on the landing page only. This segmentation allows the system to differentiate between potentially valid clicks (those with deeper engagement) and potentially invalid clicks (those with minimal engagement), thereby maintaining measurement precision while processing large quantities of click data.

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If web analytics tools use simple click counting to measure advertising performance, then the ease of operation increases, but the reliability of fraud detection deteriorates

Engineering Contradiction:
Improvesimplicity of click trackingVSAvoidreliability of fraud detection
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent implements preliminary action by establishing baseline engagement metrics and anomaly detection thresholds before analyzing click data. The system pre-configures monitoring for specific engagement patterns (page views, navigation depth, time on page) and sets predetermined criteria for identifying suspicious click patterns. This allows the system to automatically detect potential fraud without requiring complex real-time analysis, maintaining ease of operation while improving reliability.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If web analytics tools implement comprehensive engagement tracking to identify invalid clicks, then the reliability of click quality assessment improves, but the device complexity increases

Engineering Contradiction:
Improvereliability of click quality assessmentVSAvoidcomplexity of analytics system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts and focuses on a limited set of critical engagement metrics that are most indicative of valid clicks, such as navigation to additional pages and time spent on the landing page. Rather than implementing comprehensive tracking of all possible user interactions, the system selectively monitors these key behaviors. This extraction approach maintains reliable click quality assessment by concentrating on the most discriminative metrics while avoiding the complexity of tracking every possible engagement parameter.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS8880541B2Qualification of website data and analysis using anomalies relative to historic patterns
Publication Date: 2014.11.04 ADOBE INC
  • US8880541B2 patent drawing
  • US8880541B2 patent drawing
  • US8880541B2 patent drawing

AI summary

Tools and techniques are provided to assist detection of invalid clicks in website activity data. A system calculates or otherwise obtains a historic click quality characterization based on historic web analytics data. The system then identifies a click quality anomaly in the website activity data, namely, a departure from the historic click quality characterization. The identified anomalies may then be used to help guide searches for invalid clicks.