Trolling for victims online “is like throwing a fishing line,” said Special Agent Christine Beining, a veteran financial fraud investigator in the FBI’s Houston Division who has seen a substantial increase in the number of romance scam cases.
“The Internet makes this type of crime easy because you can pretend to be anybody you want to be.
Then they use what the victims have on their profile pages and try to work those relationships and see which ones develop.” The subsequent investigation led by Beining resulted in the arrest of two Nigerians posing as South African diplomats who had come to the U. to collect money from the woman on behalf of Charlie, who claimed he was paid million for a construction project he completed in South Africa.
That’s not to say they’re the most effective; many, in fact, perform grammatical acrobatics that barely qualify as English.
It turns out that all those people parsing dating profiles for grammar above all else are protecting themselves not just from bad dates, but from bad actors.
When Boko Haram kidnapped a group of school girls last spring, Winchester said, dating profile fakers would claim to be there abroad as part of a US special forces mission.
In reality, they were Nigerian con artists, hoping to be sent money to pay for a flight they would never take.“The sad reality is that the most effective scammers will tend to be the human beings who build trusting relationships over a long period of time with their targets,” says Winchester.
Suddenly I had to stop doing new features and trying to acquire new users,” in order to keep up with squashing scammers.
There was no dedicated screening service at that time, Winchester says. Well, he did along with an acquaintance, Nick Tsinonis, who already had expertise using machine learning to help match dating site users based not on their expressed preference, but on behavior.If one bot network pushes out the same garbled phrase to millions of profiles, it can quickly skew the pick-up line popularity contest.These bots aren’t necessarily looking for love, or even for a direct cash transfer; they’re often simply trying to convince their marks to install something, like an app, in a case of direct marketing gone gross.“In some ways the target isn’t really the victim of anything other than having their time wasted, and installing a game that they don’t necessarily want,” says Winchester of these bot-based shakedowns.The result, Scamalytics, is a company that’s able not only to identify a number of key profile traits—in the “low hundreds,” says Winchester—but to measure how they play against one another for a more complete picture of who’s real and who’s swindling.“Features that in isolation may not give you too much information, in combination become much more powerful,” says Winchester.“We then take the learnings from that academic exercise, and try to scale them up into a production environment that works at enormous speed.”Some of those indicators are proprietary, but a few are fairly obvious.Fake photos are usually a giveaway; when in doubt, do a reverse Google image search.