4. Introduction
MDS could visualize similarity with distance that help researcher
better understand the similarity
Logo similarity Distance
5. Matrix
Square matrix Symmetrical matrix
Row and column represents The data of upside and
the same thing bottom of diagonal are the
same
A B C D A B C D
A A 1 3 5
B B 1 2 3
C C 3 2 5
D D 5 3 5
6. Dissimilarity matrix
※ SPSS MDS could only use dissimilarity matrix
Low score represents high similarity, the lower score, the more
similarity
similarity Dissimilarity
1 5
7. MDS in market research
Category management is very important in
shopper study, adjacencies analysis is a useful
method in category management which could
understand how shoppers make sense of
categories
MDS could be used to visualize the result of
adjacencies analysis, it could use distance to
represents similarity of product or category
8. Sample
We want to illustrate relationship of a group of people
Sample Shopper study
People Product/category
Likeness Similarity
Asymmetrical matrix Symmetrical matrix
9. Questionnaire design
Please grade the likeness towards following people from 1-5, 1 represents
extremely like while 5 is extremely dislike
SPRINGER
ZIMCHEK
LANGFORD
AHGHEL
LEWIS
ROBINSON
RAO
KHOURY
DEVERS
DAEL
CUSTER
RATANA
LIAN
BELTRAN
CARRINGTON
VALENZUELA
HAMIDI ※ In adjacencies analysis product are randomly
BAKKEN
presented to respondents for them to group,
CHA
Then give assignment to them
SHEARER
14. Introduction
Social network analysis (SNA) is the methodical analysis of social
networks. Social network analysis views social relationships in terms
of network theory, consisting of nodes (representing individual actors
within the network) and ties (which represent relationships between the
individuals, such as friendship, kinship, organizational position, sexual
relationships, etc.) These networks are often depicted in a social network
diagram, where nodes are represented as points and ties are represented
as lines
CONNECTOR MAVEN SALESMAN
Connect people to Connect people through
Uses knowledge to
each other sharing knowledge
engage and persuade
17. A story: beer and diapers
There is a story that a large supermarket chain, usually Wal-Mart, did an
analysis of customers' buying habits and found a statistically significant
correlation between purchases of beer and purchases of nappies (diapers
in the US). It was theorized that the reason for this was that fathers were
stopping off at Wal-Mart to buy nappies for their babies, and since they
could no longer go down to the pub as often, would buy beer as well. As a
result of this finding, the supermarket chain is alleged to have the nappies
next to the beer, resulting in increased sales of both.
18. General concept (1/3)
ID P1 P2 P3 P4
1 bread cheese butter water
2 water milk bread noodle
3 milk noodle meat beer
4 fish softdrink frozenmeal bread
Antecedent Consequent
19. General concept (2/3)
Instances
To each rule, instances represent the number of record of
included rule’s antecedent
Support
Similar with instances, support describe percentage instead of
number
Rule support
The percentage of record of included both rule’s antecedent and
consequent
20. General concept (3/3)
Confidence
Rule support / Support
Accuracy of prediction
Lift
Confidence / Prior probability of rule’s consequent
Lift>1 is meaningful
21. Dataset
confectionery
cannedmeat
frozenmeal
cannedveg
freshmeat
homeown
pmethod
softdrink
fruitveg
income
cardid
value
dairy
wine
beer
age
fish
sex
id
1 39808 42.7123 CHEQUE M NO 27000 46 F T T F F F F F F F T
2 67362 25.3567 CASH F NO 30000 28 F T F F F F F F F F T
3 10872 20.6176 CASH M NO 13200 36 F F F T F T T F F T F
4 26748 23.6883 CARD F NO 12200 26 F F T F F F F T F F F
5 91609 18.8133 CARD M YES 11000 24 F F F F F F F F F F F
6 26630 46.4867 CARD F NO 15000 35 F T F F F F F T F T F
7 62995 14.0467 CASH F YES 20800 30 T F F F F F F F T F F
8 38765 22.2034 CASH M YES 24400 22 F F F F F F T F F F F
9 28935 22.975 CHEQUE F NO 29500 46 T F F F F T F F F F F
10 41792 14.5692 CASH M NO 29600 22 T F F F F F F F F T F
…
※ Totally 1000 records
