• Choose a category
• All
• Classic-Fiction

five-number summary49

distributive measures145

Divisive Analysis (DIANA)459, 460

divisive hierarchical method459

agglomerative hierarchical clustering versus459–460

DIANA459, 460

DNA chips512

document classification430

documents

language model26

topic model26–27

drill-across operation148

drill-down operation11, 146–147

drill-through operation148

dynamic itemset counting256

E

eager learners423, 437

Eclat (Equivalence Class Transformation) algorithm260, 272

e-commerce609

editing method425

efficiency

Apriori algorithm255–256

backpropagation404

data mining algorithms31

elbow method486

email spam filtering435

engineering applications613

ensemble methods378–379, 386

bagging379–380

boosting380–382

for class imbalance problem385

random forests382–383

types of378, 386

enterprise warehouses132

entity identification problem94

entity-relationship (ER) data model9, 139

epoch updating404

equal-frequency histograms107, 116

equal-width histograms107, 116

equivalence classes427

error rates367

error-correcting codes431–432

Euclidean distance72

mathematical properties72–73

weighted74 see alsodistance measures

evaluation metrics364–370

evolution, of database system technology3–5

evolutionary searches579

exception-based, discovery-driven exploration231–234, 235

exceptions231

exhaustive rules358

expectation-maximization (EM) algorithm505–508, 538

expectation step (E-step)505

fuzzy clustering with505–507

maximization step (M-step)505

for mixture models507–508

for probabilistic model-based clustering507–508

steps505 see alsoprobabilistic model-based clustering

expected values97

cell234

exploratory data mining. seemultidimensional data mining

extraction

data134

rule, from decision tree357–359

extraction/transformation/loading (ETL) tools93

extractors151

F

fact constellation141

example141–142

illustrated142

fact tables136

summary165

factor analysis600

facts136

false negatives365

false positives365

farthest-neighbor clustering algorithm462

field overloading92

financial data analysis607–609

credit policy analysis608–609

crimes detection609

data warehouses608

loan payment prediction608–609

targeted marketing609

FindCBLOF algorithm569–570

five-number summary49

fixed-width clustering570

FOIL359, 363, 418

Forest-RC383

forward algorithm591

FP-growth257–259, 272

algorithm illustration260

example257–258

performance259

FP-trees257

condition pattern base258

construction257–258

main memory-based259

mining258, 259

Frag-Shells212, 213

fraudulent analysis610–611

frequency patterns

approximate281, 307–312

compressed281, 307–312

constraint-based281

near-match281

redundancy-aware top-k281

top-k281

frequent itemset mining18, 272, 282

Apriori algorithm248–253

closed patterns262–264

market basket analysis244–246

max patterns262–264

methods248–264

pattern-growth approach257–259

with vertical data format259–262, 272

frequent itemsets243, 246, 272

association rule generation from253, 254

closed247, 248, 262–264, 308

finding247

finding by confined candidate generation248–253

maximal247, 248, 262–264, 308

subsets309

frequent pattern mining279

advanced forms of patterns320

application domain-specific semantics282

applications317–319, 321

approximate patterns307–312

classification criteria280–283

colossal patterns301–307

compressed patterns307–312

constraint-based294–301, 320

data analysis usages282

for data cleaning318

direct discriminative422

high-dimensional data301–307

in high-dimensional space320

in image data analysis319

for indexing structures319

kinds of data and features282

multidimensional associations287–289

in multilevel, multidimensional space283–294

multilevel associations283–294

in multimedia data analysis319

negative patterns291–294

for noise filtering318

Pattern-Fusion302–307

quantitative association rules289–291

rare patterns291