Oracle9i Data Mining Concepts -- Index

Adaptive Bayes Network (ABN), 1-2, 1-10

algorithms, 1-9

settings for, 1-20, 1-26

apply model, 2-5

apply result object, 1-29

ApplyContentItem, 3-12

Apriori algorithm, 1-4, 1-18

Association Rules, 1-2, 1-4, 1-7

sample programs, A-6

support and confidence, 1-8

Attribute Importance, 1-2, 1-4, 1-8, 1-18

sample programs, A-6

using, 2-4

attribute names and case, 1-28

attributes

find, 2-4

use, 2-4

automated binning (see also discretization), 1-2

balance

in data sample, 1-6

Bayes' Theorem, 1-12, 1-13

best model

find, 2-3

in Model Seeker, 1-14

binning, 1-32

automated, 1-2

for k-means, 1-16

for O-Cluster, 1-17

manual, 1-32

sample programs, A-7

build data

describe, 3-4

build model, 3-7

build result object, 1-29

categorical data type, 1-2

character sets

CLASSPATH, 2-1

classification, 1-4

specifying default algorithm, 3-5

specifying Naive Bayes, 3-6

CLASSPATH for ODM, 2-1

clustering, 1-2, 1-4, 1-6, 1-15

sample programs, A-5

compiling sample programs, A-22

Complete single feature, ABN parameter, 1-12

computing Lift, 1-22

confidence

of association rule, 1-8

confusion matrix, 1-29

figure, 1-29

continuous data type, 1-17

costs

of incorrect decision, 1-5

cross-validation, 1-13

data

scoring, 3-8

data format

figure, 1-25

data mining API, 1-3

data mining components, 1-3

data mining functions, 1-4

data mining server (DMS), 1-3, 1-20, 1-25

connect to, 3-3, 3-9

data mining tasks, 1-19

data mining tasks per function, 1-20

data preprocessing, 1-6

data scoring

main steps, 3-9

output data, 3-11

prerequisites, 3-8

data types, 1-2

data usage specification (DUS) object, 1-27

decision trees, 1-2, 1-10

discretization (binning), 1-32

sample programs, A-7

distance-based clustering model, 1-15

DMS

connect to, 3-3, 3-9

enhanced k-means algorithm, 1-15

executing sample programs, A-22

feature

definition, 1-10

feature selection, 1-2

features

new, 1-2

function settings, 1-20

functions

data mining, 1-4

global property file, A-11

grid-based clustering model, 1-17

incremental approach

in k-means, 1-15

input

to apply phase, 1-30

input columns

including in mining apply output, 3-13

input data

data scoring, 3-10

describe, 3-10

jar files

ODM, 2-1

Java Data Mining (JDM), 1-3

Java Specification Request (JSR-73), 1-3

key fields, 1-2

k-means, 1-2

k-means algorithm, 1-4, 1-15

binning for, 1-16

k-means and O-Cluster (table), 1-17

learning

supervised, 1-2, 1-4

unsupervised, 1-2, 1-4

leave-one-out cross-validation, 1-13

lift result object, 1-29

location access data

apply output, 3-11

build, 3-4

data scoring, 3-10

logical data specification (LDS) object, 1-27

market basket analysis, 1-7

max build parameters

in ABN, 1-11

MaximumNetworkFeatureDepth, ABN parameter, 1-11

metadata repository, 1-3

MFS, 3-5

validate, 3-6

mining algorithm settings object, 1-26

mining apply

output data, 3-11

mining apply output, 1-30

mining attribute, 1-27

mining function settings

build, 3-5

creating, 3-5

validate, 3-6

mining function settings (MFS) object, 1-25

mining model object, 1-28

mining result object, 1-28

mining tasks, 1-3

MiningApplyOutput object, 3-11

MiningFunctionSettings object, 3-5

missing values, 1-32

mixture model, 1-16

model

apply, 3-1

build

synchronous, 3-7

building, 3-1

score, 3-1

model apply, 2-5, 3-8, 3-14

ApplyContentItem, 3-12

ApplyMutipleScoringItem, 3-12

ApplyTargetProbabilityItem, 3-12

asynchronous, 3-15

data format, 2-5

generated columns in output, 3-12

including input columns in output, 3-13

input data, 3-10

main steps, 3-9

physical data specification, 3-10

specify output format, 3-11

synchronous, 3-14

validate output object, 3-14

model apply (figure), 1-23

model apply (scoring), 1-22

model build

asynchronous, 3-7

model building, 1-20

main steps, 3-3

outline, 2-2

overview, 3-3

prerequisites, 3-2

model building (figure), 1-21

Model Seeker, 1-2, 1-14

sample programs, A-5

using, 2-3

model testing, 1-21

multi-record case (transactional format), 1-24

Naive Bayes, 1-2

algorithm, 1-12

building models, 3-2

sample programs, 3-1, A-4

specifying, 3-6

nontransactional data format, 1-24

numerical data type, 1-2, 1-15, 1-17

O-Cluster, 1-2

algorithm, 1-17

sample programs, A-5

ODM

basic usage, 3-1

ODM algorithms, 1-9

ODM functionality, 1-24

ODM functions, 1-4

ODM jar files, 2-1

ODM models

building, 3-2

ODM objects, 1-24

ODM programming, 2-1

basic usage, 3-1

common tasks, 2-2

overview, 2-1

ODM programs

compiling, 2-1

executing, 2-1

ODM sample programs, A-1

Oracle9i Data Mining API, 1-3

physical data specification

build

nontransactional, 3-4

transactional, 3-5

data scoring, 3-10

model apply, 3-10

nontransactional, 3-10

transactional, 3-10

physical data specification (PDS), 1-24

PhysicalDataSpecification, 3-10

PMML

sample programs, A-6

PMML export

sample program, A-6

PMML import

sample program, A-6

Predictive Model Markup Language (PMML), 1-2, 1-3, 1-37

Predictor Variance algorithm, 1-18

preprocessing

data, 1-6

priors information, 1-5

property files

sample programs, A-10

rules

decision tree, 1-10

sample

programs

Naive Bayes, 3-1

sample programs, A-1

Association Rules, A-6

Attribute Importance, A-6

basic usage, A-3

binning, A-7

classification, 3-5

clustering, A-5

compiling all, A-25

compiling and executing, A-22

data, A-9

discretization, A-7

executing all, A-26

global property file, A-11

Model Seeker, A-5

Naive Bayes, A-3, A-4

Naive Bayes models, A-4

O-Cluster, A-5

overview, A-1

PMML export, A-6

PMML import, A-6

property files, A-10

requirements, A-2

short, 3-1

short programs, A-3

summary, A-3

using, A-7

score data, 2-5

scoring, 1-5, 1-16, 1-22

by O-Cluster, 1-17

output data, 3-11

prerequisites, 3-8

scoring data, 3-8

sequence of ODM tasks, 2-3

short sample programs, 3-1, A-3

compiling and executing, A-22

single-record case (nontransactional format), 1-24

skewed data sample, 1-5

SQL/MM for Data Mining, 1-3

summarization, 1-18

in k-means, 1-16

supervised learning, 1-2, 1-4

support

of association rule, 1-8

test result object, 1-29

transactional data format, 1-24

unsupervised learning, 1-2, 1-4

unsupervised model, 1-14

Index

A

B

C

D

E

F

G

I

J

K

L

M

N

O

P

R

S

T

U