Fraud Detection in Fintech: The Battle Against Synthetic Identity Theft

By Michael B. Cohen

Vice President of Global Operations

Synthetic identity theft is a type of fraud that involves creating a fake identity using a combination of real and fabricated personal information, such as name, date of birth, Social Security or driver’s license number, and address. The fraudsters then use the synthetic identity to apply for credit cards, loans, or other financial products and services, often with the intention of defaulting on the payments or using the accounts for money laundering.

Synthetic identity theft is one of the most challenging and costly forms of fraud for the financial industry, as it is hard to detect and prevent. According to a report by McKinsey, synthetic identity fraud accounted for 10 to 15 percent of all credit losses in the U.S. in 2018, amounting to $6 billion. Moreover, synthetic identity fraud can have long-term impacts on the victims, whose personal information is used to create the fake identities, as well as on the financial institutions, whose reputation and customer trust are damaged.

How can fintech companies combat synthetic identity theft? There is no silver bullet solution, but there are some best practices and technologies that can help. Here are some of them:

  • Use multiple sources of data to verify the identity of the applicants. Fintech companies should not rely on a single source of data, such as credit bureaus or social media platforms, to verify the identity of their customers. Instead, they should use multiple sources of data, such as biometric verification, device fingerprinting, behavioral analytics, etc., to cross-check the information provided by the applicants and detect any inconsistencies or anomalies. Biometric verification is a method of verifying the identity of a person based on their physical or behavioral characteristics, such as fingerprints, face recognition, and voice recognition, among others 
  • Implement machine learning and artificial intelligence to detect patterns and anomalies. Fintech companies should leverage machine learning and artificial intelligence to analyze large volumes of data and identify patterns and anomalies that indicate fraudulent behavior. For example, machine learning algorithms can detect if an applicant has applied for multiple credit products in a short period of time, or if an account has been dormant for a long time and suddenly becomes active.
  • Collaborate with other stakeholders to share information and best practices. Fintech companies should not work in silos, but collaborate with other stakeholders in the financial industry, such as banks, regulators, and law enforcement agencies, to share information and best practices on fraud detection and prevention. This can help create a common understanding of the problem and a coordinated response to combat it.

Synthetic identity theft is a serious threat to the fintech industry and its customers. However, by adopting a proactive and holistic approach to fraud detection and prevention, fintech companies can reduce the risk and impact of this type of fraud and enhance their competitive advantage in the market., a global fund recovery consultation service that specializes in helping victims of online scams. can assist consumers in filing a chargeback request with their bank or credit card company and can provide expert guidance and support throughout the process.