Joint RDC & UTS Research Paper Accepted Into European Machine Learning Conference

Findings on Transfer Learning in Credit Risk Chosen To Be Presented To Global Audience

SYDNEY, Australia – June 2019 – A collaborative research paper authored by Rich Data Corporation (RDC) and the University of Technology Sydney (UTS) has been accepted into the highly competitive European Conference on Machine Learning and Practice of Knowledge Discovery in Databases (ECML PKKD), cementing RDC as an industry pioneer in the use of Artificial Intelligence in the credit risk domain.

ECML PKKD is one of the leading global academic conferences on machine learning and knowledge discovery. RDC’s research paper, titled “Transfer Learning in Credit Risk”, was selected to be presented at the conference following a highly competitive peer-reviewed selection process where only 18 per cent of applications were successful.

The research was co-authored by RDC’s Chief Data Scientist, Dr Hendra Suryanto, Chief Technology Officer, Charles Guan, and Senior Software Engineer, Andrew Voumard, in collaboration with Ghassan Beydoun, Professor of Information Systems at UTS’ School of Information, Systems and Modelling.  

The paper explores the uses of transfer learning to reduce limitations for lenders when faced with limited historical lending data by leveraging knowledge from related domains from similar outcome data.

“Transfer learning allows us to try to mimic humans’ ability to adapt knowledge from past experiences and apply it to new situations is to build models to accurately score the risk of a growing number of individuals with little or no credit history,” said Dr Suryanto.  “With the research described in this paper and further collaboration with Professor Beydoun’s team, we hope to continue innovating and testing the boundaries of AI research, and specifically its application to credit risk.”

“In many new applications of AI, adequate data may not be available to produce good predictive models. This research looks at adapting past models using smaller sets of data and an overall reduced effort,” said Professor GhassanWith this solid theoretical work on adapting existing models- to be presented at PKDD, here at UTS we will jointly be executing a joint experimental program with the RDC team of experts over the next 12 months. The research will refine the approach and also tune it to decision making in an unsecured lending environment. The expertise available in RDC presents us here at UTS with a wonderful opportunity to innovate in this space. This work will potentially pave the way for AI in new applications and/or to reduce the cost of generating predictive models from existing ones.”   

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases will take place in Wurzburg, Germany, from the 16th to the 20th of September 2019.


About Rich Data Corporation

Rich Data Corporation (RDC) is a Sydney-based lending Software as a Service company which utilises deep global financial services expertise, advanced AI, and non-traditional data to deliver a next-generation credit scoring and decisioning platform.  RDC specialises in enabling traditional lenders to achieve highly profitable lending outcomes and address opportunities in credit scoring and lending in a digital world. For more information, visit


About UTS Faculty of Engineering and IT

UTS is the #1 Young University in Australia. UTS aims to develop pioneering research solutions with real benefits for business, government, the environment and communities – at home and overseas. UTS is home to nine faculties and more than 50 research centres. The UTS Faculty of Engineering and Information Technology is a world-class institution, with a reputation for quality and impact. Seven university-level research centres and six schools are renowned for expertise in areas from advanced data analytics and quantum software, to artificial intelligence and water technology.

Keep posted on our LinkedIn.

Contribute to the discussion on the future of AI and lending