By empowering all of these technologies, Brighterion brings to the market the first fraud solution that makes effective changes during run-time and adapts to new and previously unknown fraud behaviors.
|
Smart-Agents Technology |
Business Rules |
|
Neural Networks |
Optimization Suite |
|
Case-Based Reasoning |
Data Mining |
|
Fuzzy Logic |
Text Mining |
|
Genetic Algorithms |
Statistical inference and Velocity Analyzer
|
SMART-AGENTS TECHNOLOGY
Smart-Agents are systems consisting of independent entities that interact
and negotiate with each other in order to reach their individual and collective
goals. Distinct from algorithmic systems, in which the programmer defines how
the system will solve problems, Smart-Agents system determines how to find the
solution. Each agent is provided with goals that describe situations
that are desirable or undesirable. Problems are solved without extensive programming
or defining a set of specific rules.
iPrevent is the only product that uses the power of Smart-Agents technology for Fraud Prevention. Every transaction is accepted by either the bad (fraud) agent(s) or the good
(genuine) agent(s). The agents interact to determine to which category each transaction belongs.
iPrevent Smart Agents, contrary to neural networks or business rules,
can make effective changes at run-time if needed. This unique new basis of adaptation
is applied at run-time, as opposed to development/design time, or as a maintenance
activity.
Learn more
Neural Networks
Neural networks are algorithmic systems that interpret historical data to identify trends and patterns against which to compare subject cases.
iPrevent’s proprietary neural network can translate any database to neurons
without user intervention, and has significantly accelerated the speed of convergence
as compared to typical neural network algorithms, such as back propagation.
Brighterion’s neural net is incremental and adaptive, allowing the size of the
output classes to change dynamically. In addition, the iPrevent expert mode
provides a library of twelve different neural network models for use in customization.
Learn more
Case-Based Reasoning
Case-based reasoning is the use of past experiences or cases to solve new problems. A case is translated to a list of features that leads to a certain outcome. Cases are stored and organized in a database and when a similar situation arises the system can go right to the solution. The solutions to complex problems are found very quickly and accurately.
iPrevent uses a generic case-based reasoning model that can translate a database
to cases without user intervention. The cases created are used to match subject
transactions for normal/fraud determination.
Fuzzy Logic
Fuzzy logic is able to account for areas that are not clearly defined. The logic can be extended to handle partial truths in situations where the answer lies somewhere in between what is true and what is false.
iPrevent’s Fuzzy Logic technology is used in iComply, Brighterion’s regulatory
and international compliances product.
iPrevent’s Fuzzy Logic can be used to automatically create generic attributes
and enable business experts to write fuzzy rules or fuzzy constraints if needed.
Genetic Algorithms
Genetic algorithms are able to address complicated problems with many variables
and a large number of possible outcomes, by simulating the evolutionary process
of “survival of the fittest” to reach a defined goal. They operate by generating
many random answers to a problem, eliminating the worst and cross-pollinating
the better answers. Repeating this elimination and regeneration process gradually
improves the quality of the answers to an optimal or near-optimal condition.
iPrevent’s genetic algorithm has specific fraud evaluation functions for
finance, healthcare, insurance, money laundering, e-commerce and telecommunications.
Learn more
Business Rules
Business Rules, or Expert Systems, are used to store the knowledge of experts in an “If... then...” format.
RETE is the industry standard algorithm for storing rules and monitoring changes to objects rather than rules, resulting in efficient access to rules.
iPrevent is embedded with a patented rule-engine algorithm, which is nearly
nine times faster than RETE and can accept an unlimited number of rules. iPrevent
also provides the following tools to allow non-technical experts to write declarative
Rules.
Rule Builder Integrated GUI development environment for developing
and testing business rule applications.
Business Rules Language Customizable and extensible language, placing
business rules power in the hands of the non-IT business users.
Optimization Suite
Optimization is used to solve problems where linear programming is not sufficient for the task.
iPrevent’s optimization allows specific constraints to be added to the system
in order to define what is or what is not allowed in a particular outcome. As
a result, the transaction can be accepted or denied. iPrevent also provides
the following tools to allow non-technical experts to write declarative constraints.
Constraint Builder Integrated GUI development environment for developing
and testing constraint-based applications.
Constraint Language Customizable and extensible, placing constraints
power in the hands of the business non-IT users.
Data Mining
Data mining, or knowledge discovery in databases is the nontrivial extraction of implicit, previously unknown and potentially useful information from data. It is the search for relationships and global patterns that exist in large databases but are hidden among the vast amount of data. Using particular classifications, association rules and analyzing sequences; data is extracted, analyzed and presented graphically.
iPrevent’s suite of data mining algorithms provides a number of different technical approaches to address: data cleaning, sampling, clustering, learning classification rules, analyzing changes and detecting anomalies.
iPrevent’s
data mining can automatically generate business rules from the customer’s data.
Learn more
Text Mining
Text mining is the interpretation of the meaning of textual content. Effective text mining is essential for the detection of money laundering and financial market manipulation behavior.
Statistical Inference
Descriptive Statistics is the process of obtaining meaningful information from sets of numbers that are often too large to deal with directly. While it is often impossible to calculate scores for all models when searching a large model space, it is often feasible to describe and calculate scores for a few equivalent classes of models receiving the highest scores. Prediction methods for this sort of problem always assume some regularity in the probability distribution.
iPrevent uses a number of statistical methods including correlation, regression, Chi-square and others.
Velocity Analyzer
Velocity files keep track of card/check/account/merchant usage and more.
For example, if a card suddenly begins to rack up an unusually large number
of transactions, the acquirer or the issuer may send a “call me” message to
the merchant.
iPrevent Velocity Analyzer, is a powerful Tracking tool that can be used,
for example, to detect Skimming (the skimmer swipes the card through their device,
which then copies the cards magnetic stripe details into its memory) and many
other fraud collisions.
iPrevent Velocity Analyzer enables financial institutions to monitor a
wide assortment of customer and product statistics:
1. Product purchasing pattern
2. Suspicious change in card activities
3. Number of transactions over a window of time
4. Payment methods history, typical purchasing
5. Patterns at the merchant's site
6. E-mail address activity
7. Ship-to/bill-to activity
8. Refund Watch, Manual T-Log
9. Excessive Cash Back
10. Decline Analyzer
11. Excessive Failed Pre-Authorizations
12. Unattended and attended Transactions
13. Many other attributes and parameters
iPrevent Velocity analyzer uses a powerful compression technique to save
transactions for optimal scalability and performance.