Databases Reference
In-Depth Information
The software might try to discover if certain items ''fall into'' the same market
basket more frequently than would otherwise be expected. That last phrase is
important because some combinations of items in the same market basket are too
obvious or common to be of any value. For example, finding eggs and milk being
bought together frequently is not news. On the other hand, a piece of data mining
folklore has it that one such study was done and discovered that people who bought
disposable diapers also frequently bought beer (you can draw your own conclusions
on why this might be the case).The company could use this to advantage by stacking
some beer near the diapers in its stores so that when someone comes in to buy
diapers, they might make an impulse decision to buy the beer sitting next to it, too.
Another use of market basket data is part of the developing marketing discipline
of ''customer relationship management.'' If, through data mining, a supermarket
determines that a particular customer who spends a lot of money in the store often
buys a particular product, they might offer her discount coupons for that product as
a way of rewarding her and developing ''customer loyalty'' so that she will keep
coming back to the store.
Another type of data mining application looks for patterns in the data.
Earlier, we suggested that Lucky Rent-A-Car might buy demographic data about
its customers to ''enrich'' the data about them in its data warehouse. Once again,
consider Figure 13.11 with its enriched (Age, Income, and Education attributes
added) CUSTOMER dimension table. Suppose, and this is quite realistic, that
Lucky joined its RENTAL fact table with its CAR and CUSTOMER dimension
tables, including only such attributes in the result as would help it identify its most
valuable customers, for example those who spend a lot of money renting ''luxury''
class cars. Figure 13.14 shows the resulting table, with the rows numbered on the left
CAR/RENTAL/CUSTOMER
Manufacturer
Customer
Class
Name
Cost
Number
Age
Income
Education
1
Compact
Ford
320
884730
54
58,000
B.A.
2
Luxury
Lincoln
850
528262
45
158,000
M.B.A.
3
Full-Size
General Motors
489
109565
48
62,000
B.S.
4
Sub-Compact
Toyota
159
532277
25
34,000
High School
5
Luxury
Lincoln
675
155434
42
125,000
Ph.D.
6
Compact
Chrysler
360
965578
64
47,500
High School
7
Mid-Size
Nissan
429
688632
31
43,000
M.B.A.
8
Luxury
Lincoln
925
342786
47
95,000
M.A.
9
Full-Size
General Motors
480
385633
51
72,000
B.S.
10
Compact
Toyota
230
464367
64
200,000
M.A.
11
Luxury
Jaguar
1170
528262
45
158,000
M.B.A.
12
Sub-Compact
Nissan
89
759930
29
28,000
B.A.
13
Full-Size
Ford
335
478432
57
53,500
B.S.
14
Full-Size
Chrysler
328
207867
29
162,000
Ph.D.
F IGURE 13.14
Lucky Rent-A-Car enriched data, integrated for data mining
Search WWH ::
Custom Search