To date, there has been no efficient way of uncovering synthetic ID fraud. To crack down on it, every customer seeking credit would have to undergo even more rigorous ID checks than they do already. This Mckinsey 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 is on this group that banks, or indeed any organization wanting to stop synthetic ID fraud, can focus their ID checks without inconveniencing other customers.