Products & Services
Credit Risk and Bad Debt
We create custom credit risk models to help companies identify those accounts which are of higher risk and thus are more likely to default and incur significant write-offs. Our models can be used to score new and existing accounts in order to determine their associated level of default risk. Our proven solutions have been successfully adopted by cell phone service providers, leasing companies, and banks.
Urgent Fraud Management - Mitigate Data Breaches
When there is an urgent fraud issue, we identify problems and find quick fixes. For example,
after analyzing data a few days after a major card fraud incident, we proposed a solution
that prevents at least 60% of the loss in a similar future attack. In addition, a few weeks
after the historical Heartland data breach was discovered, we analyzed the data and proposed
three changes to the existing fraud prevention processes that significantly improves detection
accuracy.
Fraud Predictive Models
Our fraud predictive models run on scoring engines and calculate risk scores for transactions
or accounts. A web-based front-end user tool allows the user to review the report. The calculated
risk scores are also accessible through a web service and may be incorporated into your existing
fraud prevention system.
"If we maintain the same fraud prevention staff level, it is forecasted that the total fraud loss prevented will be up 20%." - Dr. Jay Zhou
Existing Fraud Detection System Optimization
We optimize existing fraud detection systems by adjusting parameters and identifying hidden fraud behavior patterns.
Fraud Detection Rules Optimized by Genetic Algorithms
A genetic algorithm (GA) simulates the natural evolution process to find the best solution that fits the environment. With our GA based proprietary technology, a large number of initial fraud detection rules evolve to detect more fraud at lower false positive. After many generations of evolutions, the best fraud detection rules are the ones that survive.
Customized Fraud Prevention Systems
We build fraud prevention systems that address specific areas of concerns. For example, we have built
a web application that successfully generates suspicious activity reports about analysts who handle customer claims. This is
used for monitoring internal fraud.
Vendor Evaluation
As experts, we evaluate fraud prevention solutions proposed by vendors and identify their strengths and
weaknesses so that you can make the best decision for your enterprise.
Fraud Prevention Training
We offer training classes on how to build predictive analytics solutions to business problems.
Oracle SQL and Oracle Data Mining Training