// fraud

what is The money lens: fraud detection vs bot detection?

Why the fraud model is reputation- and velocity-led rather than fingerprint-led. Bot detection asks 'is this a real browser driven by a real person?'; fraud detection asks 'will this account cost money or take an account?' The hardest adversary is a human fraud farm (real people, real phones, real fingers) that passes every bot signal, so the money lens leads with what the farm cannot cheaply rotate.. The thesis the richards fraud catalog leads with. Cross-ref: R3 vendor state.