DRIVERS NOTWANTED

摘要

Credit card fraud costs US merchants and credit card companies more than $3.4 billion a year. That figure would undoubtedly be much higher without the use of computer surveillance systems to monitor every transaction. One of the most proven antifraud systems is FICO's Falcon Fraud Manager, which keeps tabs on more than 4 billion transactions a month and uses lightning-fast neural networks to scan for suspicious purchase patterns. Neural networks were originally designed to mimic human gray matter. Over time, however, the technology has moved far beyond brain simulation to become a basic building block of many computer systems capable of learning and pattern recognition. The networks typically consist of layers of interconnected "neurons," each of which produces a signal only when its input exceeds a certain threshold. Though the individual neurons are simple, the net as a whole can learn to recognize complex patterns of inputs.