Alaric Launches ‘Self-Learning’ Fraud Solution

Oct. 24, 2011

Alaric International, a London-based technology company specializing in payments related products and services, recently released a software solution that uses self-learning technology to root out card fraud. The company said its Fractals 3.7 employs tailored user-supplied rules and sophisticated mathematical models to detect fraud. “For any given organization, a self-learning model like Fractals 3.7 will easily deliver in excess of 80 percent case detection rate at a low false positive ratio,” said Mike Alford, CEO of Alaric “A typical neural network consortium model may detect just 45-47 percent of fraud cases at an ‘acceptable’ false positive ratio. In practical terms, self-learning models can significantly save an organization’s losses to fraud, typically between 70 and 90 percent.” Alaric said the Fractals self-learning detection models can detect more than 70 percent of fraud cases on the first fraud and can reject the transaction in flight as part of the authorization process, leading to major fraud savings.