Plaid Launches Credit and Fraud Models Fueled by Cash Flow Data

Plaid, a digital finance network, has introduced new artificial intelligence models to assist financial institutions in making decisions regarding credit, fraud, and payments, according to a press release sent to PYMNTS on Tuesday (Oct. 6). One of these new models, Instant Link, enables consumers to share their cash flow insights with lenders in seconds by linking their financial accounts to Plaid's Consumer Reporting Agency.

This cash flow data provides lenders with a more comprehensive understanding of the consumer's ability to repay loans, particularly for those who do not fit the traditional credit criteria. Another model, LendScore 2 (Ls2), utilizes cash flow underwriting and predicts a borrower's repayment ability with 42% greater accuracy compared to traditional credit data alone.

Plaid has also introduced specialized models tailored for auto loans, home loans, and short-term loans. A third model, LendScore Arc, is a transformer-based credit risk model that learns from the sequence and timing of a borrower's transactions, making it Plaid's most effective credit model yet for lenders seeking to incorporate transformer-based credit modeling.

Michelle Young, Plaid's Credit Product Lead, stated that while cash flow data offers a more holistic view of a borrower, lenders have not previously had the means to access and utilize this information. Plaid has also unveiled a new AI foundation model designed specifically for fraud detection, which enhances its Protect solution.

The company's sequential foundation model now powers its ACH risk model, Protect, to better anticipate payment risks. According to the Plaid Intelligence and Plaid collaboration "Payment Protection: Why Firms Still Aren’t Real-Time Ready," 94% of surveyed firms are not yet fully prepared for new Nacha regulations requiring active fraud monitoring on the ACH network.

Plaid's Chief Technology Officer, Will Robinson, emphasized that the credit, fraud, and payments models leverage deep financial context derived from time-based financial behavior across the Plaid Network, leading to better decisions and outcomes for customers and the millions of individuals who rely on these services.