Fraud Detection: Beyond the Rules-Based Approach

Data defines the model by dint of genetic programming, producing the best decile table.

Fraud Detection: Beyond the Rules-Based Approach
Bruce Ratner, Ph.D.

Fraud on credit cards continues to grow and cuts profits by about $280 million each year. Healthcare fraud costs its industry an estimated $45 billion to $150 billion each year. These staggering figures imply that the credit card and healthcare sectors are in urgent need to adopt advanced analytic techniques in order to protect losses, and to avoid passing along these potentially avoidable costs to consumers. Currently, these sectors use the traditional rules-based (e.g., “if …then”) approach for fraud detection. However, this approach is not strong enough for the necessary data mining that would uncover undetected risk-predictive relationships. This knowledge can be used for predictive modeling with techniques, such as, statistical regression models, and artificial neural networks methods. The purpose of this article is to apply the data mining muscle, and the alongst predictive power of the new machine learning method – the GenIQ Model© – for fraud detection.

For more information about this article, call me at 516.791.3544, or e-mail, br@dmstat1.com.
My publisher owns the copyright of the article, about which this abstract addresses. The article will appear in my forthcoming book.
My publisher has granted me permission to discuss orally the article's content, but by no means provide an outline, a draft or proof-ready of the article.

Sign-up for a free GenIQ webcast: Click here.