The aim of the conference is to explore the advantages of granular data to detect vulnerabilities in the financial system and to openly debate its potential with relevant stakeholders. The conference will host presenters from the private and public sector as well as from academia.
Programme for the conference on the use of credit register data for financial stability purposes and credit risk analysis, 24 October 2019, in Copenhagen.
Registration and breakfast
Opening Remarks: Governor Per Callesen, Danmarks Nationalbank
|09:10-10:40||Session 1: Financial stability|
Diana Bonfim - Banco de Portugal and Católica Lisbon SBE
“Inspect what you expect to get respect” Can bank supervisors kill zombie lending?
Rob Nijskens – De Nederlandsche Bank
Loan level data and their link with the macro-economy
Mikel Bedayo - Banco de España
Loan underwriting time: a new determinant of bank lending standards
Key note speaker
Steven Ongena - University of Zurich, Swiss Finance Institute, KU Leuven, CEPR
On Applications Using Credit Registers
|12:45-14:15||Session 2: Credit Risk Modelling|
Gerhard Winkler - Oesterreichische Nationalbank
The usage of credit register data for credit risk modelling: applications and experiences of OeNB
Joannes Paulus Wilhelmus Buckens & Søren Topp Stockmann - Danske Bank
An industry perspective on the use of credit modelling today; what’s changed in recent years and where could we go?
Fabrizio Russo - 4Most Europe Ltd
Credit Risk Modelling – Data and techniques used in the UK banking industry
|14:35-16:05||Session 3: Machine Learning applications for Financial Stability|
Giorgio Mirone - Danmarks Nationalbank
Households credit assessment model
Mirko Moscatelli/Fabio Parlapiano - Banca d'Italia
Corporate Default Forecasting with Machine Learning
Rogelio Mancisidor – University of Tromsø
Deep Generative Models for Reject Inference in Credit Scoring
|16:20-17:00||Panel discussion: The use of credit registry for financial stability and supervisory issues|
Open debate on the use of credit registry for supervisory issues and to what extent credit register data will aid policy makers in making informed decisions and how it can support supervisory actions.