Love is the most lucrative online fraud.

Online scammers set camp on dating sites and lure their victim into believing they found someone special. Once a love connection has been established, requests for money follow. The reason for requests range from medical emergency to travel costs for a long-awaited visit to meet their true love.

A team of U.K. researchers claims it has created an algorithm with the ability to understand what fake dating profiles look like. The algorithm can apply this knowledge to scan demographic information, photos, or bios on dating sites to weed out a fake profile. The algorithm could prevent thousands from being catfished online.

The research is led by experts from the University of Warwick and funded by the Engineering and Physical Sciences Research Council (EPSRC) and the Economic and Social Research Council (ESRC).

Romance-cons are on the rise

According to reports filed with the Federal Trade Commission (FTC), hopelessly romantic Americans looking for love lost at least $143 million to scammers last year. The median reported loss was $2,600 – seven times more than the amount lost for other types of frauds tracked by the FTC.

online dating scams

The FTC advises people against sending money to people they haven’t met in-person.

In the same year, over 3,000 Britons lost a total of £41 million (52 million USD) to online dating scams, with an average loss of £11,500 (14,718 USD).

Professor Sorell says: “Online dating fraud is a very common, often unreported crime that causes huge distress and embarrassment for victims as well as financial loss. Using AI techniques to help reveal suspicious activity could be a game-changer that makes detection and prevention quicker, easier and more effective, ensuring that people can use dating sites with much more confidence in future.”

The FTC offers the following tips to anyone who fears they may be a victim of an online dating scam:

  • Don’t send money to anyone you haven’t met in-person.
  • Ask questions and look for inconsistencies in their answers.
  • Try a reverse-image search of their profile pictures.