Perspectives

Ping An OneConnect Bank (PAOB) is launching a one-year pilot program to accelerate the SME financing process in Hong Kong.

Working with Hong Kong Applied Science and Technology Research Institute (ASTRI), PAOB will introduce a Federated Learning-based credit assessment model. The model will provide credit assessors with a large data set of micro, small and medium-sized enterprises (MSMEs) while protecting the data privacy of the businesses.

What is Federated Learning?

As a privacy-preserving technology, Federated Learning is an artificial intelligence (AI) model that can speed up the financing process for MSMEs Federated Learning does not require data to be transferred to a central database, so it protects the data privacy of MSMEs and reduces the risk of data security breaches.

As a pioneer in the virtual banking sector for MSMEs, PAOB has already introduced MSME financing innovations with the use of alternative credit scoring, which utilizes AI-backed methods to analyze data repositories to make dynamic credit assessments. PAOB recently completed its first year of operation.

A Federated Learning-based approach will take it a step further as collaborators will not have direct access to any personal data nor would the enterprises be identified. Not only will it ensure privacy, it will build trust between institutions. With access to a larger data set that is privacy-protected, financial institutions will be able to make better credit decisions as well.

This is one example of how PAOB works to empower partners to better serve the MSMEs of Hong Kong. By working with forward-thinking technology enabler like ASTRI and continuing to apply technological innovations in financial technology, PAOB is taking the industry one step closer to achieving financial inclusion in Hong Kong.

This website uses cookies to help us provide you with better experience and allow us to improve our service. By continuing to browse the site, you understand and agree to our Privacy Policy and Terms of Use .

This website is not supported by IE. Get the latest version of Firefox or Chrome for better browsing experience.

Noted