Document Type: Framework
Status: Active
Authority: Research Brain
Parent: Research Brain Canon
Applies To: All research analysis, journey analysis, signal extraction, and pattern detection across MWMS
Version: v1.0
Last Reviewed: 2026-05-02
Purpose
The Research Brain Outlier Journey Intelligence Framework defines how MWMS identifies, analyzes, and learns from unusual or extreme user journeys.
The purpose is to:
- uncover hidden behavioural patterns
- identify high-value and low-value journey structures
- detect anomalies that reveal opportunity
- improve understanding of user behaviour
- feed intelligence into optimization and scaling systems
This framework ensures MWMS learns from:
→ what stands out
not just:
→ what averages show
Scope
This framework applies to:
- user journey analysis
- attribution data review
- conversion path analysis
- behavioural signal interpretation
- research and pattern discovery
It governs how outliers are interpreted and used, not how data is collected.
Core Principle
Averages hide opportunity.
Outliers reveal insight.
Definition — Outlier Journey
An Outlier Journey is:
a user journey that significantly differs from the typical pattern in behaviour, engagement, or outcome.
This includes:
- unusually high-value users
- unusually low-value users
- unexpected conversion paths
- extreme engagement behaviour
Outlier Categories
1. High-Value Outliers
- significantly higher spend
- repeated conversions
- deep engagement
- long lifecycle
Purpose:
→ identify what drives value
2. Low-Value Outliers
- low engagement
- no conversion
- early drop-off
- poor journey quality
Purpose:
→ identify friction and failure
3. Behavioural Extremes
- unusually high number of touchpoints
- unusually short paths to conversion
- unusual sequence of interactions
Purpose:
→ uncover alternative journey structures
4. Anomaly Events
- sudden spikes
- unexpected drops
- rare behavioural patterns
Purpose:
→ detect new opportunities or issues
Analysis Approach
Outlier analysis must focus on:
- behaviour patterns
- journey structure
- sequence of actions
- timing and frequency
Avoid focus on:
- personal identity
- demographic assumptions
- irrelevant attributes
Pattern Extraction Rule
The goal is not to understand the individual.
The goal is to extract:
→ reusable behavioural patterns
Key Questions
For each outlier, ask:
- what actions did they take
- what sequence did they follow
- what made them different
- what signals indicate similar behaviour
- can this behaviour be replicated
Signal Identification
Outlier journeys must be translated into signals:
- high-value signals
- friction signals
- engagement signals
- conversion triggers
These signals must feed into:
- Research Brain signal systems
- Experimentation Brain test design
- Affiliate Brain optimization
Opportunity Identification
Outliers can reveal:
- new landing page ideas
- new funnel structures
- new messaging angles
- new targeting opportunities
Feedback Loop
Outlier insights must be:
- documented
- tested
- validated
- integrated into system learning
Integration With Other Brains
Outlier intelligence must feed into:
Experimentation Brain
- test new journey hypotheses
- validate patterns
Affiliate Brain
- optimize traffic sources
- refine audience targeting
Data Brain
- refine scoring systems
- improve signal classification
Frequency Rule
Outlier analysis must be:
- ongoing
- not one-time
MWMS must continuously scan for:
- new patterns
- changing behaviours
Cognitive Discipline Rule
Avoid over-interpreting outliers.
Outliers must:
- be validated through data
- be tested before scaling
- be confirmed as repeatable patterns
Drift Protection
The system must prevent:
- reliance on averages only
- ignoring extreme behaviour
- overfitting to single cases
- using anecdotal insights without validation
- focusing on individuals instead of patterns
Architectural Role
This framework operates within:
- Research Brain (primary)
- Experimentation Brain (validation)
- Affiliate Brain (application)
- Data Brain (signal refinement)
It acts as the discovery layer for:
→ new behavioural intelligence
Relationship To Other MWMS Standards
This framework works alongside:
- Research Brain Signal Classification Framework
- Research Brain Research Verdict Framework
- Experimentation Brain Structured Testing Protocol
- Data Brain Visitor Value Scoring Framework
Architectural Intent
The Research Brain Outlier Journey Intelligence Framework ensures:
- MWMS identifies hidden opportunities
- behaviour is understood beyond averages
- system learning improves over time
- new growth paths are discovered
It moves MWMS from:
→ average-based understanding
to:
→ pattern-driven intelligence
Change Log
Version: v1.0
Date: 2026-05-02
Author: Research Brain
Change:
Created Research Brain Outlier Journey Intelligence Framework to define how MWMS extracts insight from extreme and unusual user journeys.
Change Impact Declaration
Pages Created:
Research Brain Outlier Journey Intelligence Framework
Pages Updated:
None
Pages Deprecated:
None
Registries Requiring Update:
MWMS Architecture Registry
Canon Version Update Required:
No
Change Log Entry Required:
Yes
END OF DOCUMENT