A very interesting application of high-fidelity synthetic data generation techniques is to reduce credit card fraud. By 2025, the global losses to credit card fraud are expected to reach almost $50 billion. Detecting fraudulent transactions in a large data-set poses a problem because they are such a small percentage of the overall transactions. Banks and financial institutions are in need of a solution that can correctly identify both fraudulent and non-fraudulent transactions, and detect false/true negatives and false/true positives, enabling the creation of receiver operating curves and tuning the system to optimize for the cost to correct the fraud payment versus the cost of the payment. High fidelity synthetic data solves this dilemma by generating volumes of non-fraudulent transactions while interweaving complex fraud patterns into a very small subset of the overall transactions. The fraud patterns are known, enabling the credit card fraud detection system to be optimized.
High interest helping to implement Cyber Behavioral Tools was expressed by many potential clients, including the Cyber Innovation Manager from one of the world's largest banks, a Divisional Chief Information Security Officer for one of the biggest US Federal Systems Integrator's and one of the largest Cyber Independent Testing Laboratories. During the demonstrations large amounts of internally consistent data was generated for all desired behaviors. Data was generated over any time-frame to output: