Investigative Data Mining for Security and Criminal Detection

False negatives, 221

False positives, 195–96, 221

defined, 195

measuring, 298

minimizing, 195

Federated databases, 329–30

Financial crime MOs, 277–79

bank fraud, 279

card-not-present fraud, 277–78

credit-card fraud, 277

loan default, 278

See also Modus operandi (MO)

Financial Crimes Enforcement Network (FinCEN), 53, 84, 86

analysts, 86, 87

Artificial Intelligence System (FAIS), 107

consideration and aggregation use, 87

database access, 88

data restructuring, 86

link analysis use, 86–88

Fire debris analysis steps, 174

Forecasting, 160

Forensic data mining, 375–76

Forensics, 324–25

Fping, 305

Fraud

auction, 254–56

bank, 279

battle, 273

card-not-present, 277–78

clustering, 262–63

conditions for, 269–70

credit-card, 250–51, 277

decision trees and, 268–69

defined, 275

ensemble, 271

insurance, 281–87

mitigates on-line, 250

profile, 251–52

risk scores and, 252

rules, 253–54

statistics, 268

telecommunications, 288–90

viewing, 261–62

Fraud and Abuse Detection Engine (FADE), 154

Fraud detection, 264–66

data enhancement, 259–60

data extraction, 259

deterrence activities, 275

hybrid solution, 272–73

mining tools, 261

neural networks in, 264–66

outsourcing option, 271–72

in real-time, 249–50

services, 257–58

signature and, 272

system, building, 258

transactional data and, 253