Explore is a series of webinars which has been created to provide a platform for organisations to hear from leading researchers at the University of Edinburgh. The series will see multi-disciplinary academics share their expertise, discuss the latest advances and present cutting-edge innovations relevant to your organisation.
The evolution of fintech (the application of technology in financial services) is replacing and refreshing many aspects of traditional banking. Technological advances and new regulations have substantially altered how financial services are and will be delivered. Innovative businesses are taking advantage of fintech to develop new services that give consumers more choice about how they manage their money.
Explore: Fintech webinar series offers an opportunity for companies in the finance, investment and banking sectors to discover the latest technologies and advances in research that have potential to transform current business models and support recovery and growth following the economic impact of the Covid-19 pandemic.
Explainable Artificial Intelligence. Compromising Accuracy?
Speaker: Dr Belen Martin-Barragan
In recent years, we have witnessed a quick rise on the use of artificial intelligence (AI) and advance statistical techniques in the financial industry. These techniques provide a predictive power that is well beyond what we expected with the classical techniques.
Although predictive ability is important, obtaining an easy-to-interpret classifier is also crucial in many applications. Indeed, current regulations acknowledge the ‘right-for-explanation’ of a customer that got the credit denied.
This talk will discuss solutions to attain explainable AI-based predictors without giving up on predictive accuracy.
DR BELEN MARTIN-BARRAGAN is a Lecturer in Management Science and an expert in interpretable machine-learning classifiers. She is currently the PI on EPSRC-funded project ‘Optimization models for interpretable analytics’. She has published 9 peer-reviewed papers in reputed academic journals. In the last 5 years, she has been successful in securing grants totalling £370K, of which £284 came from UKRI councils.
The future for credit risk modelling methodologies
Speaker: Prof Jonathan Crook
In this webinar, prof Jonathan Crook discusses the developments and opportunities for predicting credit risk including:
- The use of transactions data for modelling the individual’s journey to default and distress, for predicting affordability, for modelling exposure at default and loss given default and for stress testing portfolios of loans.
- Stress testing individual loans to pandemics and climate change.
- The use of new data sources and new predictors for credit risk prediction.
- Bias in scoring models. Models are built on accepted applicants and lenders are well aware of the possible need for reject inference. But there is potentially a much larger group that is excluded leading to so, far, unrecognised bias. The talk explains what it is and how to deal with it.
PROF JONATHAN CROOK is Professor of Business Economics, Director of the Credit Research Centre at the University of Edinburgh as well as Deputy Dean and Director of Research at the University of Edinburgh Business School.
He has researched into credit scoring and the demand and supply of credit since the late 1980s. He has published over 60 refereed journal articles, mostly in the areas of credit scoring and credit availability. He has also co-authored or co-edited five books including Credit Scoring and its Applications, 2017 (with Lyn Thomas and David Edelman), a standard reference book for practitioners and Masters Students.
He is interested in all areas of credit risk modelling, especially the incorporation of macroeconomic factors into credit risk modelling, stress testing (including with respect to climate change and pandemics), survival models, dynamic models, the demand and supply of credit and the use of new forms of data including transactional data. He has research projects in each of these areas, in many cases with financial organisations.
Jonathan is the lead organiser of the biennial Credit Scoring and Credit Control conference. He has received research grants from the EPSRC, ESRC, Fulbright and other sources. He is a Fellow of the Financial Institutions Center at the Wharton School, University of Pennsylvania and an External Research Fellow of the Centre for Finance, Credit and Macroeconomics at the University of Nottingham.
He is a Fellow of the Royal Society of Edinburgh and a Fellow of the Academy of Social Sciences. He has acted as a credit scoring consultant to a number of banks. For nine years he was a joint Editor of the Journal of the Operational Research Society.
Adapting and navigating support for people in financially vulnerable situations: a digital tool
Speaker: Prof Tina Harrison
Navigating and providing financial support is a demanding task for all involved. Those in vulnerable situations can be easily overwhelmed with the quantity of information and trying to understand what is suitable for them. Support organisations have to balance the struggle of accuracy of the information and making sure it is as digestible and accessible as possible, whilst keeping information up to date in changing landscapes. Digital support tools can provide a user-centred approach that helps manage these difficulties and can provide data that helps improve and evolve the services to continually improve.
Sopra Steria and Prof Tina Harrison have partnered to develop a financial support tool for those in vulnerable situations. During this webinar, we will share the current research in this area and provide a demo of the current support tool being developed. We will then encourage questions from attendees to bring to our panel discussion aimed at surfacing the main barriers that need to be overcome in this area and what approaches have worked best in the past.
This session is chaired by Stephen Ingledew, Chief Executive at Fintech Scotland. It also includes Kerry Nicolaides from Sopra Steria and Mickael Piears from DWP.
PROF TINA HARRISON is Professor of Financial Services Marketing and Consumption. She has over 25 years’ experience researching financial services consumers and financial services behaviour. Her research has specifically focused on individuals’ use and understanding of financial services and the role of technology in this respect.
Recent projects include a three-year ESRC-funded project on the impact of the internet on the pensions industry; a two-year ESRC-funded Seminar Series on Financial Services and Consumers; an analysis of young adult financial capability for Money and Pensions Service; a two-year evaluation of the impact of professional learning on school-based financial education with Young Money/Money and Pensions Service. She is co-editor of The Routledge Companion to Financial Services Marketing and was Editor-in-Chief of the Journal of Financial Services Marketing for 18 years.
How Open Banking can increase access to finance during Covid-19
Speaker: Dr Raffaella Calabrese
The Covid-19 pandemic has increased the need for external finance for individuals and small businesses. However, given the high economic uncertainty, financial institutions are reluctant in proving credit. A new accurate model is proposed to improve the lending assessment based on open banking data. Recommendations to help rejected applicants to improve their financial security and capability are also provided. Finally, a continuous monitoring system that will track customers’ financial situation, behaviour and credit risk will be suggested. Then, the system will offer proactive recommendations and will propose lower interest rates if users are able to reduce their credit risk by following positive financial habits.
DR RAFFAELLA CALABRESE’s research and collaborations with industry (such as Moody’s Analytics, Nationwide, RBS, Barclays, SAS and Bank of England) are focused on developing new models for analysing credit risk and Fintech data. The former includes scoring models, modelling of loss given default, stress testing and interpretability. Raffaella has applied a variety of methods to measure default risk for SMEs and for retail credit in the context of Basel II and III. She is also working on interpretability for machine learning techniques and use of alternative data (e.g. social media or mobile data) in the credit risk framework.
For Fintech, she has proposed novel solutions to assess risk using Open Banking data such as affordability test and credit scoring. She is a member of the Credit Research Centre and part of the Fintech team at the Edinburgh Futures Institute.
Grey rhinos in financial markets: the case of Covid-19
Speaker: Dr Gbenga Ibikunle
How well financial markets perform their key functions of providing liquidity to facilitate hedging, diversification, and saving, and efficient price discovery to direct resources to their best uses within the economy, affects every individual’s financial well-being. A major fraction of all retirement savings is invested in global stock markets either directly or indirectly. Job growth, incomes, and therefore our standard of living depend on corporate investment, the financing of which in turn depends on well-functioning financial markets. Therefore, investigating the market quality effects of a grey rhino like the Covid-19 pandemic is of economic value from a number of perspectives, including investments and policymaking.
In this webinar, we will discuss the effects of the Covid-19-induced shock in financial markets on aggregate value selection/market share and market quality. We will examine how the shock is linked with an economically significant loss of market share by dark pools to lit exchanges. In line with theory, the loss appears linked to an increase in lit market volatility and a search for immediacy by traders active in stocks with dark trading access. The market quality implications of the reduction in dark trading are mixed: while it tempers Covid-19-linked liquidity decline in the lit market, it exacerbates the loss of informational efficiency.
DR GBENGA IBIKUNLE is an Associate Professor of Financial Markets at the University of Edinburgh, the Director for Industry, Economy and Society at the Edinburgh Futures Institute, the Deputy Scientific Director at the Fondazione European Capital Markets Cooperative Research Centre in Pescara and a Research Fellow at the RoZetta Institute in Sydney. His work on the microstructure of high-tech financial markets has been of much interest to both practitioners and policymakers, leading to regular speaking engagements and collaborations with financial institutions and market regulators, including at the Financial Conduct Authority (FCA), where he was a Research Visitor in 2016 and 2017.
His research papers on dark pools and interest rate swaps were published by the FCA in 2017. Gbenga has also held Visiting Professorships at Macquarie University, Sydney, Universidade Catolica Portuguesa, Porto and China University of Petroleum Beijing.