Join NexChange - the professional
network for the financial services
industry - and receive a free one-
year subscription to Forbes
China’s First Digital Bank Teams up With HK Startup to Develop ‘Federated Learning’ AI
FinTech, AI, Financial Services
Tencent-backed WeBank, China’s first digital bank, is currently developing new models in artificial intelligence called “federated learning,” DigFin reports.
Traditional machine learning requires all the data to be centralized into one machine or datacenter. This, however, can be privacy-intrusive especially for banks and devices which store sensitive information.
Federated Learning on the other hand is designed for decentralized data, allowing users to train their shared models on scattered datasets while keeping all the sensitive info to themselves.
Here’s how it works:
Using federated learning, multiple banks jointly develop a model based on sub-models in each bank’s individual environment.
Let’s say a customer applies for a loan from Bank A. The bank’s credit officer has no way of knowing whether the applicant is already borrowing from other banks. But the co-developed algorithm could produce a general credit score suggesting this customer is risky. However, the algorithm doesn’t have the customer’s credit record, because each bank owns part of the record and therefore replies part of the question, while all related information is encrypted. Then it’s up to Bank A to either serve her a loan at a higher interest rate, or decline her altogether.
Chen Tianjian, deputy general manager for A.I. at WeBank, claims that their new model has halved defaults among the company’s loans.
Helping WeBank develop its federated learning framework is a start-up called Clustar. Based in Hong Kong, Clustar is an A.I. infrastructure startup which boasts investments from big-name investors like Sequoia China and Stone VC. It was founded in 2018 by Chen Kai, an associate professor at the Hong Kong University of Science and Technology (HKUST).
“We’ve chosen Clustar because there is very few companies in the market that can at the same time provide solutions for both network transmission optimization and computational optimization,” said Chen Tianjian.
Photo: uberof202 ff