TransUnion Research Highlights Power of Public Data in Uncovering $3.3B Synthetic Identity Threat

Core Insights - The rise of synthetic identities has led U.S. lenders to face over $3.3 billion in exposure for the year ending 2024, highlighting the urgent need for enhanced fraud detection methods [1] - TransUnion's research indicates that public data attributes can significantly aid in identifying synthetic identities, which are often constructed using a mix of real and fabricated information [2][3] Group 1: Synthetic Identity Fraud - Synthetic identities are created using stolen Social Security numbers, fictitious names, and digital contact details, making them difficult to detect with traditional verification systems [2] - The complexity of synthetic identity fraud arises from the lack of a single method used by criminals, complicating the differentiation between genuine and synthetic customers [3] Group 2: Detection Strategies - Key living characteristics, such as the absence of vehicle ownership or voter registration, can indicate a higher likelihood of an identity being synthetic, with such traits appearing in 30-50% of synthetic identities [4] - TransUnion's Synthetic Fraud Model is designed to identify public data indicators and risk factors to uncover synthetic identities early in the customer journey, allowing for proactive measures [5] Group 3: Operational Efficiency - The model enhances operational efficiency by reducing manual reviews and customer friction, enabling lenders to improve fraud detection rates while streamlining processes [6] - By identifying the absence of real-life attributes, lenders can prevent fraud and minimize financial losses throughout the customer lifecycle [7]