Revolut CEO says its proprietary models are trained on customer transaction data
Revolut CEO Nik Storonsky said at an event in Turin that Revolut uses techniques similar to those used for large language models to build proprietary models trained on customer transaction data, according to a Reuters report. He said Revolut has 30 to 40 million transactions every day. PYMNTS reported in April that Revolut trained a PRAGMA model on 40 billion transactions.
NoteFor banks, transaction data may matter most for fraud and credit models, the kind of decisions PYMNTS says Revolut's PRAGMA model makes.
Read the original
The Morning Note, by email
The AI-in-finance stories that matter, before work
One short email each morning, readable in under three minutes. Free, and you can leave anytime.