Fraud Analytics Using Descriptive, Predictive, and Social Network Techniques: A Guide to Data Science for Fraud Detection

Index

A

1. Absolute deviation
2. Account data
3. Account management database, information storage
4. Accuracy ratio (AR)
   1. AUC, linear relation
   2. calculation, example
5. Acquisition costs
6. Activation functions
7. Actual fraud, predicted fraud (contrast)
8. Adaptive boosting (Adaboost) procedure
9. Adjacency list
10. Adjacency matrix
    1. mathematical representation
11. Administrative activities (fire incident claims)
12. Administrators, experts (collusion)
13. Affiliation networks
14. Age
    1. default risk, contrast
    2. regression model
    3. split, entropy (calculation)
15. Agglomerative hierarchical clustering
    1. divisive hierarchical clustering, contrast
    2. methods, usage
16. Aggregate loss distribution
    1. description
    2. indicators
    3. Monte Carlo simulation
17. Alert Type
18. Analysis of variance (ANOVA) test
19. Analytical fraud models
    1. backtesting
    2. calibration, backtesting
    3. design/documentation
    4. life cycle
    5. performance metric, monitoring
    6. stability, backtesting
20. Analytical model life cycle
21. Analytics, strategic contribution
22. Anomaly detection
23. Anticipating effect
24. Anti-fraud steering group
25. Anti-money laundering setting, cash transfers (clustering)
26. Approval activities (fire incident claims)
27. Approval cycle, absence
28. AR. See Accuracy ratio
29. Area under the ROC curve (AUC). See also Multiclass area under the ROC curve
    1. calculation (performance metric)
30. Assignment decision. See Decision trees
31. Association rule analysis
32. Association rules
    1. consideration
    2. examples
33. Attrition, problem
34. AUC. See Area under the ROC curve
35. Autoregressive integrated moving average (ARIMA)
36. Average ...