• Advancing Cash Flow Underwriting With Instant Link and LendScore 2, Delivering 42% More Predictive Lift Than Traditional Credit Data Alone
• New AI Foundation Models Sharpen Fraud Detection and Payment Risk Assessment

Plaid, the network that powers digital finance, today unveiled new AI models that help financial firms make better lending decisions, catch more fraud, and reduce payment risk, as part of its annual Fall Product Release.

Plaid launched Instant Link, which lets consumers share financial insights with lenders in seconds, alongside an expanded LendScore suite of credit risk models, including LendScore 2 and LendScore Arc, its first transformer-based credit risk score. Plaid also introduced a new AI foundation model for fraud detection, now powering Plaid Protect, and extended its sequential foundation model to payment risk through Signal and Guaranteed Payments.

The foundation models benefit from the breadth of Plaid’s network, which spans thousands of financial institutions and millions of consumers, providing exposure to a wide variety of financial formats, income levels, and economic behaviors needed to learn patterns that generalize across real financial lives.

"Our credit, fraud, and payments models are unique because they bring deep financial context to every problem they're solving," said Will Robinson, CTO at Plaid. "They build on foundation models that already understand how financial behavior unfolds over time, across the Plaid Network, and that means better decisions, and better outcomes, for our customers and the millions of people who depend on those services to manage their own financial lives."

Smarter lending with faster data sharing and more predictive models

Millions of US adults fall outside of the traditional credit lens, making them difficult to evaluate with traditional credit scores alone. Cash flow data shows how people earn, spend, and pay their bills, giving lenders a fuller picture of their ability to repay.

Plaid is introducing three advances in cash flow underwriting:

• Faster insights sharing with Instant Link: Added steps during a credit application can result in borrower drop off. With Instant Link, borrowers who connect their financial accounts to Plaid Consumer Reporting Agency can consent to share their cash flow insights for future credit applications, creating a faster experience. Lenders have access to those insights in under two seconds.
• Sharper credit decisions with LendScore 2 (Ls2): Plaid’s new core model is 42% stronger at predicting a borrower’s ability to repay a loan compared to traditional credit data alone. New specialized models extend those gains for specific industries: Ls2 Auto lowered delinquency by 26% among deep-subprime applicants at the same approval rate. Ls2 Home Lending approved 6.3% more borrowers at the same level of risk, bringing cash flow underwriting into two markets that have historically relied almost entirely on traditional credit data. The LendScore family also includes a model purpose-built for short-term lending.
• More advanced risk modeling with LendScore Arc: Powered by Plaid’s sequential foundation model, Arc is a transformer-based credit risk model that learns from the order and timing of a borrower’s transactions, making it Plaid’s best-performing credit model yet, for lenders ready to leverage transformer-based credit modeling. In early testing, we saw that Arc delivers significant predictive lift over our core model, including 20% lift on deep subprime and 24% lift on superprime borrowers.

“Cash flow data tells a more complete story about a borrower. The challenge has been turning that story into insights that lenders can access and act on with speed and confidence,” said Michelle Young, Credit Product Lead at Plaid. “The next generation of LendScore and specialized models close that gap at scale, and with Arc, we’re giving lenders new tools to expand access to more affordable credit.”

Extending the same intelligence to fraud and payments

The Fall Product Release brings these advances beyond credit, helping businesses detect fraud and make more confident payment decisions. Fraud often emerges from a sequence of seemingly routine actions. A new AI foundation model purpose-built for fraud now enhances Plaid's fraud detection solution, Protect. Trained on patterns and hundreds of millions of data points from the Plaid Network, it analyzes the full sequence of events rather than a snapshot to strengthen the Trust Index, Protect's existing scoring framework. In internal evaluations, it delivered up to 40% relative improvement over previous baselines.

Plaid’s sequential foundation model also powers Signal, Plaid's ACH payment risk model, which reads an account's transaction history in sequence to better predict payment risk. In testing, the sequential foundation model helped Signal prevent 26% more ACH returns without increasing false flags. Guaranteed Payments uses that sharper risk analysis to give businesses more flexible approval options, including delayed release and partial guarantees, rather than a single approve-or-decline decision.

About Plaid

Plaid powers the tools millions of people use to lead healthier financial lives. Our solutions help build a more inclusive, competitive, and resilient financial system by simplifying payments, transforming lending, and advancing the fight against fraud. More than 9,000 companies, including leading fintechs, Fortune 500 enterprises, and many of the largest banks, rely on Plaid to give people greater choice and control over their money. Headquartered in San Francisco, Plaid connects to over 12,000 financial institutions across the US, Canada, the UK and Europe.

View source version on businesswire.com: https://www.businesswire.com/news/home/20261006091265/en/

Plaid LendScore 2 delivers 42% stronger predictive performance than traditional credit data alone.