Credit risk modeling: Leveraging technology advances for enhanced credit risk modelling

Credit risk modeling: Leveraging technology advances for enhanced credit risk modelling

By Shannon Kelly, SVP, Director, Model Risk Management, Zions Bancorp

Can you please tell the Risk Insights readers a little bit about yourself, your experiences and what your current professional focus is?

My experience Is In model development and validation across different risk types, including credit, market and operational risk. My current role Is the Head of Model Risk Management at Zions Bancorp.

What, for you, are the benefits of attending a conference like Risk Americas and what can attendees expect to learn from your session?

Attendees can expect to better understand what technologies support CECL implementation, from databases to implementation platforms. Platforms (vendor provided or internal) have different features, including transparency/traceability in calculations as well as the ability to run multiple scenarios.  However, the features of any one platform differ, requiring the bank to assess its requirements in selecting/designing the technology solution for CECL implementation and credit risk management.

How can technology be used to advance credit risk modeling, what are some potential uses?

CECL can be used for what If scenario analysis to provide management with information on potential losses under different plausible scenarios for risk management and pricing.  Additionally, CECL models can be used to make strategic decisions by analysing the allowance levels required for different portfolio compositions.  Technology platforms can provide rapid Implementation and reporting of such analysis.

What factors need to be considered when evaluating cost efficiency and sustainability?

Initial cost efficiency and sustainability need to consider the transparency of the platform and customizability.  For initial cost effective a platform could have limited features with transparency into the calculations, and then features could be customized over time to make the solution sustainable.  Having too many features and customization up front can lead to continual rebuilds, especially for a vendor-maintained platform.

How have risk profiles evolved with the changes in customer behaviour?

Risk profiles have evolved to incorporate more drivers to identify changes In behaviour, as customer behaviour and credit risk have expanded with more available credit, short-term, unsecured credit and greater risk appetite.  Re-payment behaviour Is also more aligned to incentives and social norms. For this reason, more complex behavioural drivers and patterns should be identified in current credit attribute data as well as alternative bureau sources.

How does technology look to impact availability of credit, can it be utilized as a tool for rating beyond traditional factors?

Technology can assist in gathering data from multiple sources and rapidly identifying patterns beyond the current body of knowledge. This can help support extension of credit to underserved populations as well as identify which traditional customers are the best credit risks.  Technology can better analyse non-traditional data sources, with the right discipline to the analysis.

How do you foresee technology impacting the risk and modeling landscape?

Technology will speed up the development/validation cycle so that emerging trends can be identified quickly and so that model reliability can be improved through rapid updates and deeper analyses into underlying behaviours. Technology can also mitigate the risk of identifying false relationships by conducting more robust analysis as well as identifying data bias and anomalous trends quickly.