finance_ops · finance · workflow
Nubank deploys billion-parameter Foundation Models across predictive decision engines in first eight months after Hyperplane acquisition
Nubank historically relied on linear models, gradient-boosted trees, and aggregated tabular features for predictive AI decisions, which could not capture complex behavioral signals, limiting the bank's ability to advance to an AI-first model.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Hyperplane acquisition triggers project
Nubank acquired Hyperplane in July 2024 to integrate Foundation Model technology into the bank.
Tools used
Ray
Outcome
Over the initial project period, Nubank achieved a +1.20% AUC lift across benchmark tasks—described as 2~3x the lift for a mature model's typical annual release—and deployed large-scale transformer-based sequence models to several key decision engines, all without adding any new data source.
Results
Volume+1.20%
Running sinceJuly 2024
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes.
predictive analyticsbank statementbuilder submittedmetric backednamed customerproduction runtime claimedtools describedworkflow describedbankingaccuracy improvementtechnical build writeupfinance opsdata sync enrichment