Beruflich Dokumente
Kultur Dokumente
Discovery: Personalization
Technologies for One to
Bhagi Narahari
One Marketing
Outline of Lecture
How ?
Personalization
Predictive Modelling
Model
(Crystal ball?)
Why DM?
CRM
CRM
CRM
Personalization in Ecommerce
Positive:
Negative:
Personalization
Customer Chain
Product
Discovery
Customer Service
& Support
Product
Evaluation
Order
Payment
Terms
Negotiation
Market
Research
Order
Placement
Customer Service
& Support
Market
Stimulation/
Education
Producer
Chain
Order billing
and payment
management
Terms
Negotiations
Order
Receipt
Deliver
Use of Personalization
Impact of Personalization
Customer relationship
Learn more about customers
Personalization
Know the Customer
Questionnaires
Past history
Click Streams
Identify
Login
Credit Card#
Profile
Mapping to
peers
Product
selection&
promotions
Extrapolation
from past
New
Product
Extrapolation
from peers (firefly.com)
Cookies
Registration
Key Question:
Two drivers
Two parts
Common data
demographics (country,zip,age,gender)
Contact (name, address, CreditCard)
User agent preferences
Per-site Sections (can be shared across sites, if user
allows)
What if no profile???
Deduce
Predict behaviour
mining is key!
Personalization: Actions to
take- Look and feel
Personalized pages
specific data
specific presentation and design
sent through various mediums
Manage Customers not products: 1-1 marketing
Strategy.com
Storefront Personalization
Pants
Johns View
Womens
Childrens
Casuals Evening
Infants
Marys View
Kids
BroadVision.com
DM Terminology
Rule Based Systems
OLAP
Data Marts
ROLAP
Data Warehouse
SQL
Data Stores
Genetic Algorithms
Neural Networks
Data Mining
How?
KDD
KDD
Pre-processing in KDD
Classification/Segmentation
Binary (Yes/No)
Multiple Category (Large/Medium/Small)
Typical DM tasks
Directed
Decision trees, Neural networks, memory based
reasoning, logistic regression
Examples:
How many units will be sold on a given day?
What will be the stock price on a given day?
Will a customer buy the product or not?
DM tasks
Affinity grouping
Undirected
Which products go together naturally?
The beer-diaper syndrome?
Market basket analysis
Examples:
Which products peak in demand
simultaneously?
DM tasks
Clustering task
Undirected
Segmenting into similar clusters
Different from classification
Examples
Customers with similar buying profiles
Products with similar demand patterns
DM success factors
Privacy concerns
Making Decisions
Data
Data
Data
Data
Data Warehouse?
Models
Decisions
Data Warehouse
Bill Inmon: A data warehouse is a subjectoriented, integrated, time-variant, nonvolatile collection of data in support of
management decisions.
is managed data that is situated after and
outside the operational systems
Data Warehousing
Data Complications
Noise
Missing data
Transformation
numeric data
text
Relational vs
Multidimensional
Consolidations
Multidimensional
Terminology
Data
Data
Data Loader
Data Converter
Data Scrubber
Data Transformer
Data Warehouse
OLAP Server
OLAP Interface
Cluster Detection
Transaction data
Customer
Products
Milk, Soda
Milk, Beer,
diapers
Milk, cleaner
3
4
5
Beer, diapers,
soda
Beer, soda
Co-occurrence matrix
Beer Clean Milk Soda Diapers
er
Beer 3
0
1
2
2
Clea 0
Milk 1
Soda 2
Diap 2
MBA example
Decision Trees
Balance<10K
yes
Age< 48
No
Age > 48
yes
Step 1:
Step 2:
Benefits of Integration
Summary