AI News Today.

Other

ANZ Bank · NVIDIA

Independently reportedBanking & financePilotEnterpriseClassical ML

Independently reported. An independent or peer-reviewed source reports this result, alongside the vendor.

Reported by bestpractice.ai (independent reporting). Checked against the source page on 2026-09-06. 2 of 2 figures below appear on that page word for word.

The problem

Banks' historical methods for assessing risk (application scoring and behaviour scoring) are limited by data availability, accuracy, amount, and frequency of reassessment.

What was deployed

Vendor
NVIDIA
Products
Nvidia DGX-1 platform, Nvidia Tesla P100 GPUs, TensorFlow
Technique
Classical ML
Build or buy
Bought and customised
Deployment
On-premise
Data used
customer credit card data from 1 million accounts
Scale
1 million accounts for data, 200,000 accounts for testing

What changed

Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.

0.82Gini coefficient for assessing riskfrom 0.78

“raising the Gini coefficient used in assessing risk from 0.78 to 0.82.”

Quoted word for word from the source

30 minutesTime to test model

“Testing the model with some 200,000 accounts took only 30 minutes.”

Quoted word for word from the source

“before the bank moves forward with its neural network-based model, a number of health checks need to be cleared.”
— Jason Humphrey

Difficulties and limits

Sources

Similar deployments

Unilever · Google Cloud

15-35% increase — retailer sales

Independently reportedOther · Other · Classical ML · Scaled

BHP Billiton

zero — accidents due to driver drowsiness

Independently reportedOther · Other · Classical ML · In production · 2022

Cubo Ai · Google Cloud

more than 10X — user growth supported with same IT workforce

Vendor-reportedOther · Other · Computer vision · Scaled · 2019