London-based Alaric has launched Fractals, a payment card fraud detection solution which uses 'Bayesian' probability theory to uncover credit card misuse.
Alaric says the use of Bayesian methods offers significant advantages over neural network-based systems: Fractals models may be computed in a matter of minutes, thus enabling them to be adaptive and to keep pace with changing fraud patterns, as a result of which elapsed time and costs are radically reduced; and it can operate on data from a much smaller number of cardholders, putting the technology in reach of institutions with small to mid-sized cardholder bases.
Mike Alford, Alaric's managing director, adds: "The unique Bayesian approach adopted for Fractals enables fraud officers to interpret the system's reasoning behind a given fraud alert easily and quickly, in contrast to the sometimes impenetrable black box approach associated with neural networks."
Fractals can be delivered as an in-house solution or via Alaric's ASP service.
London-based Alaric was re-launched in 2001 with a cash injection by Northern Venture Managers.