4. Decision tree
Nodes are labelled with attribute
names, edges are labelled with
values of attributes that satisfy some
condition and ‘leaves’ that contain an
intensity factor which is defined as
the ratio of the number of
transactions that satisfy these
condition(s) over the total number of
legitimate transaction in the behavior
5. Genetic algorithms and other algorithms
Basically, this method follows the scoring process.
diagnostic algorithms, diagnostic resolution strategies, probabilistic curve
algorithms, best match algorithms, negative selection algorithms, and density
selection algorithms.
6. Clustering techniques
In this method, system cluster the same behavioral accounts by researching
transactions for some period. The hypothesis of the peer group analysis is that if
accounts behave the same for a certain period of time and then one account is
behaving significantly differently, this account has to be notified.
7. Neural networks
Train the neural network with each account transactions using methods like
Back-propagation. To identify patterns, Data mining tools(such as ‘Clementine’)
allow the use of neural network technologies, which have been used in credit
card fraud.
8.
9. Example System Solutions
1. FSS
● FSS Toggle - Real time Card blocking, transaction limiting, transaction
blocking features(geographical range), blocking payment delivery channels
such as in-store, e-Commerce, ATM etc.
● FSS Access Control Server - Reduce fraudulent transactions by providing an
additional layer of authentication for cardholders. Real-time transaction
alerts.
● ATM/POS Monitoring - Monitoring and real time alerting
10. 2. Banksoft
The possible performance of any new scenario can be calculated on a scenario
simulator that uses data from past actions, and once the new scenario is
optimized, it can be transported to online scenario batches. The in-depth
analysis of suspicious transactions helps determine future component and
scenario scores.
11. Banksoft Functional Features
● Rule-based structure
● Dynamic scenarios to enable real-time authorization intervention
● Score infrastructure to grade suspicious activities
● Action differentiation according to risk levels
● In-depth analysis of chip data
● Early warning system
12. Enterprise Fraud Management (EFM)
Enterprise fraud management (EFM) software supports the detection, analytics
and management of fraud across users, accounts, products, processes and
channels.
It monitors and analyzes user activity and behavior at the application level
(rather than at the system, database or network level), and watches what
transpires inside and across accounts, using any channel available to a user. It
also analyzes behavior among related users, accounts or other entities, looking
for organized criminal activity, fraud rings, corruption or misuse.
14. FIS Card & Emerging Payments Fraud
● Dynamically block suspicious transactions as they occur.
● Adjust alerts as threats specific to your institution emerge.
● Quickly regain control after a breach by selectively blocking accounts,
automatically communicating with affected cardholders, expediting new
plastics and creating the audit trail.
● Create and monitor a customized plan that keeps you on top of fraud trends.
● Influence customer behavior and reduce collections based on behavioral
scores.
● Seamless migration to personalized EMV chips. It decreased counterfeit
card fraud
15. FIS Fraud Protection for Checks
● Empower client tellers to stop fraud at the teller line by reviewing on-screen
signature cards.
● Identify suspicious checks and account activity with sophisticated fraud
filters and neural-network technology that detect fraud before it becomes a
loss.
● Catch suspicious items with filters that flag high dollar, special watch, new
account, non-MICR etc.