Java Data Mining Concepts - Java Data Mining: Strategy, Standard, and Practice - page 138

Table 7-3 Customer attrition build data

Average saving
account balance Customer id Age Capital gain Attrite

1 41 $4,500 $11,500 Attriter

2 35 $15,000 $3,000 Non-attriter

3 26 $3,400 $21,500 Attriter

4 37 $6,100 $36,000 Attriter

5 32 $14,500 $7,000 Non-attriter

6 40 $2,500 $15,000 Attriter

7 30 $11,000 $6,000 Non-attriter

8 21 $4,100 $2,000 Non-attriter

9 28 $10,000 $5,500 Non-attriter

10 27 $7,500 $31,500 Attriter

1

Age > 36 Age <= 36

2 3

A TTRITER N ON - ATTRITER

Saving balance >=
$21,500

Saving balance <
$21,500

4 5

N ON - ATTRITER A TTRITER

Figure 7-3 Decision tree for customer attrition.

Confidence is the ratio between the cases with correct predictions in the
node and the total number of cases assigned to that node. The support
value is a measure of how many cases were assigned to that node from
the build dataset. Support can be expressed as a count or the ratio
between the number of cases in the node and the total number of cases
in the build dataset.