MWMS MCR

Data Brain Personalization Measurement Framework

Document Type: Framework
Status: Active
Version: v1.0
Authority: HeadOffice
Applies To: Data Brain, Ecommerce Brain, Customer Brain, Conversion Brain, Ads Brain, Experimentation Brain
Parent: Data Brain Canon
Last Reviewed: 2026-05-02

Purpose

The Data Brain Personalization Measurement Framework defines how MWMS collects, structures, and uses data to enable effective personalization across the user journey.

Personalization without measurement is guesswork.

This framework ensures personalization is:

  • data-driven
  • measurable
  • accurate
  • actionable

Core Principle

You cannot personalize what you do not understand.

You cannot understand what you do not measure.

Definition

Personalization Measurement:

The structured process of collecting and analysing user data to determine:

  • who the user is
  • what the user wants
  • where the user is in the journey
  • how the system should respond

Role Within MWMS

This framework powers:

  • Ecommerce Brain Personalization Journey Framework
  • Customer Brain segmentation systems
  • Conversion Brain action design
  • Ads Brain targeting
  • Experimentation Brain testing

Measurement First Rule

Before any personalization is applied, MWMS must answer:

  • Who is the user?
  • Where did they come from?
  • What are they trying to do?
  • What stage are they in?
  • What signals are available?

If these questions cannot be answered:

→ personalization must not be applied

Data Types

1. Zero Party Data

Definition

Data intentionally provided by the user.

Examples

  • quiz responses
  • preference selections
  • survey inputs
  • account details
  • declared interests

Value

  • high accuracy
  • high intent
  • explicit signals

Rule

Zero party data should be actively collected when value exchange exists.

2. First Party Data

Definition

Data collected from user behaviour.

Examples

  • pages visited
  • clicks
  • time on page
  • cart actions
  • purchase history
  • navigation patterns

Value

  • behavioural insight
  • scalable
  • continuous

Rule

First party data must be continuously tracked and structured.

3. Contextual Data

Definition

Data based on user environment.

Examples

  • location
  • device
  • browser
  • time of day
  • referral source

Value

  • immediate relevance
  • supports real-time personalization

Rule

Contextual data must be used to adjust experience dynamically.

Measurement Categories

Identity Signals

  • new vs returning
  • logged in vs anonymous
  • known vs unknown user

Intent Signals

  • search terms
  • category selection
  • filter usage
  • product views

Behaviour Signals

  • click patterns
  • dwell time
  • repeat visits
  • cart actions

Value Signals

  • purchase frequency
  • order value
  • lifetime value
  • engagement level

Stage Signals

  • awareness stage
  • consideration stage
  • decision stage
  • post-purchase stage

Data Collection Points

Entry Points

  • ads
  • search
  • referral links

On Site Behaviour

  • homepage interaction
  • navigation behaviour
  • product interaction
  • cart behaviour

Conversion Points

  • checkout
  • form completion
  • purchase

Post Purchase

  • thank you page
  • tracking page
  • email interaction
  • SMS interaction

Measurement Flow

Data Collection
→ Signal Classification
→ Segmentation
→ Personalization Decision
→ Action
→ Measurement Feedback

Segmentation Requirement

All measurement must feed segmentation.

Segmentation types include:

  • behavioural
  • intent-based
  • value-based
  • need-based

Rule

Data without segmentation:

→ is not usable for personalization

Signal Quality Rule

All data must be evaluated for:

  • accuracy
  • relevance
  • recency

Low-quality data must not drive personalization.

Privacy And Consent Rule

Personalization must operate within:

  • user consent
  • legal requirements
  • transparency

Key Principle

Privacy improves personalization quality by:

→ focusing on zero and first party data

Measurement Output

The system must produce:

  • user classification
  • segment assignment
  • journey stage
  • personalization recommendation

Cross Brain Integration

Data Brain
→ owns measurement

Customer Brain
→ interprets user

Ecommerce Brain
→ applies personalization

Conversion Brain
→ optimises action

Ads Brain
→ aligns targeting

Experimentation Brain
→ validates outcomes

Failure Modes Prevented

  • random personalization
  • incorrect assumptions
  • irrelevant messaging
  • poor targeting
  • wasted traffic
  • broken user experience

Drift Protection

The system must prevent:

  • personalization without data
  • using outdated data
  • ignoring user intent
  • over-reliance on assumptions
  • collecting data without purpose

Architectural Intent

This framework ensures MWMS:

→ measures before acting
→ understands before personalizing

It transforms data from:

→ raw signals

into:

→ structured intelligence

Final Rule

If the data is unclear:

→ the system must default to neutral experience

Change Log

Version: v1.0
Date: 2026-05-02
Author: HeadOffice

Change:
Created Personalization Measurement Framework defining zero party, first party, and contextual data usage for structured personalization.

Change Impact Declaration

Pages Created:
Data Brain Personalization Measurement Framework

Pages Updated:
None

Pages Deprecated:
None

Registries Requiring Update:
Data Brain Page Registry

Canon Version Update Required:
No

Change Log Entry Required:
Yes

✅ END