An article from McKinsey starts by saying that, rather than using a stolen credit card or ID, many fraudsters now use fictitious, synthetic ID to draw credit. McKinsey estimates synthetic ID fraud is the fastest-growing type of financial crime in the US, accounting for 10 to 15% of charge-offs in a typical unsecured lending portfolio, and says that much bigger losses are building up behind these IDs like hidden time bombs. The article proposes a new approach that, with the help of machine learning, digs deep into vast amounts of third-party data to gauge whether the basic information given by an applicant matches that of a real person, thereby weeding out the small proportion of those likely to be using a synthetic ID. It says that a synthetic ID is created by applying for credit using a combination of real and fake, or sometimes entirely fake, information. Though this application is typically rejected because the credit bureau cannot match the name in its records, the very act of applying for credit automatically creates a credit file at the bureau in the name of the synthetic ID, so the fraudster can now set up accounts in this name and begin to build credit.