Plaid launches credit and fraud models, lifting loan repayment prediction 42%
Plaid launched its new credit and fraud models on Tuesday, saying LendScore 2 improves loan repayment prediction by 42% over traditional data and that Instant Link enables real‑time cash‑flow sharing. The Instant Link model lets eligible consumers share cash‑flow insights with lenders in seconds, while a new AI foundation model aims to strengthen fraud detection by learning from patterns across the Plaid Network.
LendScore 2 uses cash‑flow underwriting and is said to predict repayment ability with 42% greater strength than traditional credit data alone. LendScore Arc, a transformer‑based model introduced Tuesday, learns from the order and timing of borrowers’ transactions and is described as Plaid’s best‑performing credit model yet. Specialized versions of the models are now available for auto, home and short‑term loans. Plaid’s sequential foundation model now powers its ACH risk product Protect to better predict payment risk.
“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,” Michelle Young, Plaid Credit Product Lead said.
“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,” Will Robinson, Plaid Chief Technology Officer said.
In June, PYMNTS reported that lenders are shifting to models built around real‑time behavior, arguing that what a consumer earns and owes today matters more than their credit score from six months ago. The same PYMNTS Intelligence and Plaid collaboration found that 94% of surveyed firms are not yet fully compliance‑ready for new Nacha rules requiring active fraud monitoring on the ACH network. This gap has prompted Plaid to build models that turn cash‑flow data into actionable credit and
What we know
LendScore 2 predicts repayment ability with 42% greater strength than traditional credit data alone.
Instant Link lets eligible consumers share cash flow insights with lenders in seconds.
Plaid announced Tuesday the availability of a new AI foundation model purpose‑built for fraud.
The PYMNTS Intelligence and Plaid collaboration found that 94% of surveyed firms are not yet fully compliance‑ready for new Nacha rules.
Plaid’s sequential foundation model now powers its ACH risk model Protect to better predict payment risk.