10. Inference
• Hypothesis becomes Rule :
Customers who buy bread and butter,
also buy milk.
• With 75% confidence and 50% support
from past transactions records
13. Bank customer Data set
Case Age Income Risk Credit Result
1 20 52,623 –38,954 red 0
2 26 23,047 –23,636 green 1
3 46 56,810 45,669 green 1
4 31 38,388 –7,968 amber 1
5 28 80,019 –35,125 green 1
6 21 74,561 –47,592 green 1
7 46 65,341 58,119 green 1
8 25 46,504 –30,022 green 1
9 38 65,735 30,571 green 1
10 27 26,047 –6 red 1
RISK = ASSETS – DEBT – WANTS
14. Bank’s weight for each attribute
and condition for analysis
Attribute Weight
Function Percentage
Credit 0.800
Minimum
Risk 0.700 25
Support
Income 0.550 Minimum
90
Age 0.450 Confidence
Result 0.691
Objective : Provide Confident/Risk
factor for the bank to issue loans for
the customers
16. Fuzzification
Attribute Level Representation Weight Membership Support
value (Rjk)
Age Young R11 0.450 0.580 0.261
Age Middle R12 0.450 0.300 0.135
Age Old R13 0.450 0.131 0.059
Income High R21 0.550 0.000 0.000
Income Middle R22 0.550 0.890 0.490
Income Low R23 0.550 0.109 0.060
Risk High R31 0.700 0.457 0.320
Risk Middle R32 0.700 0.208 0.146
Risk Low R33 0.700 0.332 0.233
Credit Good R41 0.800 0.720 0.576
Credit Bad R42 0.800 0.280 0.224
Result On Time R51 0.691 0.930 0.643
Result Default R52 0.691 0.069 0.048
17. Item set
• C = complete sets, individual items
• L = Set of items above minimum support,
grouped items
• minsupp = 0.25
• Conditional probability = support
18. Apriori Algorithm
START
Compute
Eliminate
conditional
items < minsupp
probability of each
to form SET L
element in SET C
Is
L=0 YES : STOP
NO : nCr to form
new SET C
27. Defuzzification
• If Income is middle, then payment will be
received on time
R22->R51;(91.6%)
• If Credit is good, then payment will be
received on time
R41->R51;(97.2%)
• If Income is middle and Credit is good, then
payment will be received ontime
R41, R22-> R51; (99.5%)
• If Risk is high and Credit is good, then
payment will be received on time
R31, R41->R51; (99.25%)