Professional Documents
Culture Documents
Data Mining
+++
http://www.monografias.com/trabajos55
/mineria-de-datos/mineria-dedatos2.shtml
Lecture 1 Introduction
Agenda
Course Description
Course Logistics
Case discussion
Theories/Methods
Data
Applications
Market
Hands-on Experience
SAS
Enterprise Miner
3
Course Objectives
Agenda
Course Description
Course Logistics
Case discussion
Course Logistics
Qing Li
TA
kooliqing@gmail.com
Jia Wang
xiaojiajia198796@gmail.com
Office hours:
Walk-in
By appointment
Before and after class
Call me
Class Resources
Class homepage:
http://liqing.cai.swufe.edu.cn/
post slides,
announcements, downloads
Text Book
Data Mining Techniques: For Marketing, Sales, and
Customer Relationship Management, Second Edition
Michael Berry and Gordon Linoff, 2004, Wiley, ISBN
0471-470643
Class Schedule
Topic
1
Misc. Topics
Guest Speaker
10
Two phases
Phase
Software
11
Grading
15%
Participation
50%
3: Excellent
2: Good
1: OK
0: Absent with good reason and advance notification
-3: Absent with no reason
Homework
2 big assignments
Problem solving, data analysis and/or case discussion.
25% each
35%
Term Project
(No Curve)
12
Misc. Issues
13
Survey
14
Agenda
Course Description
Course Logistics
Case discussion
15
Discussion Questions:
1.
2.
3.
4.
16
Discussion Questions:
1.
2.
3.
4.
17
Case 3: SUV
Discussion Questions:
1.
2.
3.
4.
18
Agenda
Course Description
Course Logistics
Case discussion
19
What is a pattern?
Marketing
Telecommunications
Retail
Healthcare
Customer Support
22
Safeway:
Pfizer pharmaceuticals:
Cross selling, when a customer calls, know what other services to offer
Build models to figure out what makes a loyal customer
These models saved a marginally profitable bill-paying service
Amazon:
Construct a predictive model which tells patients their cholesterol risk score.
High risk patients can request Lipitor, Pfizers cholesterol medication.
Fidelity:
Recommendations
Capital One:
Mature
data mining
technology
DM
Improved Data
Collection
& Storage
25
Big Names:
Smaller Companies:
ANGOSS KnowledgeStudio
XLMiner
MegaPuter PolyAnalyst
DBMiner
http://www.kdnuggets.com
26
Dont expect clean data. Data cleaning accounts for 70% of efforts
Implementation problems:
Other problems
3, Take Action
targeted customers
Prioritizing customer service
Cingular and AT&T were fined for $1.5 million on Sept. 10, 2004
for discriminating their services based on customers credit rating.
Adjusting
inventory levels
Rearrange products on the shelves
Verizon sends out 40k mails to selected customers per
month
30
4, Measuring Results
32
33
34
Get data
Clean/correct data
Assess Models
Computational issues
Implementation issues
Availability of relevant and amount of data
Do we have the necessary expertise
Do a market test
37
Inability to act upon patterns because of political, legal and ethical reasons
38
Simpsons Paradox
Male
Business School
Admit
Deny Total
480 (80%) 120 (20%)
600
Male
Female
180 (90%)
Female
20 (10%)
200
Law
Admit
Deny Total
10 (10%) 90 (90%)
100
100 (33%) 200 (66%)
300
Read Chapter 1, 2, 3
Read cases for Lecture 2
Install SAS
Find a group member for your term
project and start thinking about which
company to select for your project
40