We are pleased to offer all delegates the opportunity to select two out of four pre-conference workshops to attend (please select when you register):
- Integrating Credit Risk and Finance 17:00 - 18:30
This session will teach attendees how to adjust their credit score development to enable integration with Finance so that pricing and cut-off scores can be optimised.
Joseph L. Breeden, CEO, Deep Future Analytics LLC & President, Model Risk Managers’ International AssocationIntegrating Credit Risk and Finance
Objectives
This session will teach attendees how to adjust their credit score development to enable integration with Finance so that pricing and cut-off scores can be optimised.
Topics
- Understanding why good credit scores alone cannot prevent unprofitable lending.
- The “Last Mile” Problem in Lending: Addressing the challenge of connecting credit risk scores with financial cash flows.
- Risks of Misalignment.
- Best practices for transforming cross-sectional credit scores into panel data to generate account-level cash flows.
- Solving for Cut-off Scores and Pricing using algorithmic connections.
- Applying Survival and Age-Period-Cohort Models methods to logistic regression, Stochastic Gradient Boosted Regression Trees, and Neural Networks to improve predictive power.
- Converting ML credit scores into ML cash flow models to enhance long-term accuracy.
- Early Warning Systems for Residual Risk by origination pool.
Benefits of attending
This workshop will provide valuable insights to the credit risk and control community by:
- Integrating Proven Methods: Reviewing key modelling techniques that have been presented and published, including at past CSCC Conferences, and demonstrating how they can be combined to address core business challenges.
- Bridging the Implementation Gap: Highlighting why these methods, while individually interesting, are rarely implemented and showing how they can be applied to solve the “last mile” problem of setting cut-off scores or pricing.
- Detailing Estimation Techniques: Explaining estimation processes, including public domain algorithms, to equip participants with actionable knowledge for real-world application.
Who should attend?
- Model developers seeking to build credit risk models with greater applicability across their organisations.
- Managers seeking to integrate modelling efforts across credit risk, finance, and underwriting.
Format
The session will be interactive with questions and discussions at various points.
Presenter and Bio
Joseph L. Breeden, CEO, Deep Future Analytics LLC, President, Model Risk Managers’ International Association
Dr Breeden has been designing and deploying risk management systems for loan portfolios since 1995. He founded Deep Future Analytics in 2011, which focuses on portfolio and loan-level forecasting solutions for pricing, account management, stress testing, and CECL; serving banks, credit unions, and finance companies. He is also the owner of auctionforecast.com, which predicts the values of fine wines using a proprietary database with over 4.5 million auction prices.
He is a member of the board of directors of Upgrade, a San Francisco-based FinTech; an Associate Editor for the Journal of Credit Risk, the Journal of Risk Model Validation, the Journal of Risk and Financial Management and the journal AI and Ethics; and President of the Model Risk Managers’ International Association.
Dr Breeden invented vintage analytics for lending in 1997 and created credit risk models through a broad range of global crises. These experiences have provided Dr Breeden with a rare perspective on crisis management and the analytics needs of executives for strategic decision-making. In 2018 Dr Breeden invented Multihorizon Survival modelling, combining vintage analytics with behaviour scoring using logistic regression or machine learning.
Dr Breeden earned a PhD in physics, and has published over 90 academic articles, 8 patents, and 6 books, including Redesigning Credit Risk Modeling to Achieve Profit and Volatility Targets published in 2024.
He can be reached via LinkedIn or through his company Deep Future Analytics.
- Multi-Modal Deep Learning in Banking: Leveraging Artificial Intelligence for Next-Generation Financial Services 17:00 - 18:30
This workshop will dive into multimodal model using transfer learning and information fusion methodologies to understand multimodality's role in banking and evaluate its performance using Python.
Cristián Bravo, Professor and Canada Research Chair in Banking and Insurance Analytics, Department of Statistical and Actuarial Sciences, Western University
María Óskarsdóttir, Lecturer, School of Mathematical Sciences, University of Southampton & Associate Professor, Department of Computer Science, Reykjavik UniversityMulti-Modal Deep Learning in Banking: Leveraging Artificial Intelligence for Next-Generation Financial Services
Objectives
The objective of this workshop is to provide attendants with the current best practices of designing multimodal deep learning models. We will discuss the techniques and models available, plus the technical and organizational requirements to train successful models.
Topics
- Introduction of multi-modal learning and its relevance in banking.
- Overview of relevant data sources, where each one appears in banking, why they are a source of untapped profit.
- Market and regulatory landscape leveraging these data.
- Methodological description of the methods, their development, deployment, and challenges.
- Tutorial on how to build and train a simple multi-modal model.
Benefits of attending
The workshop will give a methodological overview and a hands-on tutorial on building multi-modal deep learning models for credit scoring in the context of mortgage lending. At the end of the workshop, participants will be able to:
- Understand what multimodality is and its role in banking.
- Understand information fusion methodologies.
- Develop a multimodal model using transfer learning and information fusion and evaluate it using Python.
Who should attend?
- Financial Industry Professionals: This includes professionals working in banks, credit unions, microfinance institutions, and other financial services companies who are involved in risk management, credit analysis, and innovation.
- Academic Researchers and Students in financial data science and analytics: This covers graduate students, PhD candidates, and researchers specializing in finance, computer science, data science, and related fields.
- Data Scientists and Machine Learning Engineers, particularly those working in or aspiring to enter the banking sector.
- Fintech Entrepreneurs and Startups: Innovators looking to disrupt or enhance traditional banking services with AI and machine learning applications.
Format
The session will be interactive, showcasing the code and discussing the best practices and outcomes. A practical toy exercise with an interactive notebook on how to build and train a simple multi-modal model will be given.
Presenters and Bios
Cristián Bravo, Professor and Canada Research Chair in Banking and Insurance Analytics, Department of Statistical and Actuarial Sciences, Western University
Dr Cristián Bravo is a Professor and the Canada Research Chair in Banking and Insurance Analytics at the University of Western Ontario, Canada. He also serves as the Director of the Banking Analytics Lab.
His research lies at the intersection of data science, analytics, and credit risk, researching how techniques such as multimodal deep learning, causal inference, and social network analysis can be used to understand relations between consumers and financial institutions.
He has over 75 academic works in high-impact journals and conferences in operational research, finance, and computer science.
He serves as an editorial board member in Applied Soft Computing and the Journal of Business Analytics and is the co-author of the book “Profit Driven Business Analytics”, which has sold over 6,000 copies to date. Dr. Bravo has been quoted by The Wall Street Journal, WIRED, CTV, The Toronto Star, The Globe and Mail, and Global News. He is also a regular panelist at CBC News’ Weekend Business Panel where he discusses the latest news in Banking, Finance and Artificial Intelligence.
He can be reached via LinkedIn, by Bluesky @cribravo.bsky.social, or through his lab website.
María Óskarsdóttir, Lecturer, School of Mathematical Sciences, University of Southampton & Associate Professor, Department of Computer Science, Reykjavik University
María Óskarsdóttir is a Lecturer at the School of Mathematical Sciences, University of Southampton, an Associate Professor at the Department of Computer Science at Reykjavík University and an Adjunct Professor at Western University, Canada. She holds a PhD in Business Analytics from the Faculty of Economics and Business at KU Leuven in Belgium.
Her research is focused on the intersection of network science and machine learning, looking at practical applications of data science and analytics whereby she leverages advanced machine learning techniques, network science, and various sources of data with the goal of increasing the impact of the analytics process and facilitating better usage of data science for decision making in various domains, such as finance, learning, marketing, health care and sustainability. She has over 40 publications in high-impact journals and conferences in the domains of operations research, network science and information systems. She serves as an editor at Machine Learning
She can be reached via LinkedIn.
- How Things Work in Practice 18:30 - 20:00
This workshop will explore four areas where the “theory” or the design must be tempered with some reality and business constraints and objectives.
David B. Edelman, Founder, Caledonia Credit ConsultancyHow Things Work in Practice
Objectives
This workshop will explore four areas where the “theory” or the design have to be tempered with some reality and business constraints and objectives.
Topics
- What practical considerations should we have when selecting characteristics for our modelling? What are the properties that a characteristic should have?
- What are some of the options we use in selecting the cut-off? For example, should we aim for maximum profit, or maximum growth or what?
- What is Up-Selling? What impact might there be on performance, data management, reputation, case management, and responsibilities?
- How does Risk Based Pricing work? What is its impact on the business? How much should we charge?
Benefits of attending
Attendance at this workshop will introduce to the participants several key relevant issues – such as responsible lending, stability, fairness, data quality, and operational and regulatory constraints.
Participants will emerge with a deeper understanding of how credit scoring modelling and/or implementation can be improved in their business; for others, it simply opens up their minds to issues to be addressed and hurdles to be cleared, and this helps the delegates to appreciate better some of the topics in the papers presented during the three days of the conference that follow.
In previous presentations of similar workshops at previous conferences, the audience has engaged in a healthy debate and discussion.
Who should attend?
- Those completely new to scoring, credit risk and the lending industry.
- Model developers who would like a better understanding of the practical impacts of and contexts for their models.
- Experienced practitioners who would like to refresh their thinking or challenge their ideas.
Format
The session will be interactive with questions and discussions at various points.
Presenter and Bio
David B. Edelman, Founder, Caledonia Credit Consultancy
Caledonia Credit Consultancy offers training – both bespoke and “off-the-shelf” - consultancy, interim management, and data audits, and all to a wide range of clients around the world. The goal is to work with clients to improve their understanding of the application of scoring and to improve the performance of client businesses.
David has written six books and more than 30 published articles. He has also delivered a large number and wide variety of training courses, from a 1/2-day course for boards of banks to a 5-week course for future leaders of credit business in a global bank.
His textbooks include:
- Credit Scorecard Development and Maintenance, 2021 David Edelman and John Lawrence Kindle – Amazon Kindle Direct Publishing
- Credit Scoring and its Applications, second edition 2017 (with a Chinese language edition) Lyn C. Thomas, David B. Edelman, and Jonathan N. Crook SIAM ISBN 9781611974553
David can be contacted at davide24@ntlworld.com
- An Introduction to Macroeconomic Variable Modelling within Regression Scorecards 18:30 - 20:00
This workshop will offer an in-depth examination of methodologies for incorporating macroeconomic variables into credit risk modelling, developing a clear conceptual and practical understanding of key techniques.
Luke Stanislaus, Risk Analyst at Nationwide Building SocietyAn Introduction to Macroeconomic Variable Modelling within Regression Scorecards
Objectives
Explore methodologies for incorporating macroeconomic variables into credit risk modelling and understand their practical application in regression scorecards. Develop a clear conceptual framework and actionable techniques, including recalibration and Interaction Variables.
Topics
- Data Sourcing and Preprocessing: identifying reliable sources (e.g., Bank of England, ONS), managing data lag and volatility, and applying smoothing techniques.
- Macroeconomic Recalibration of a Credit Risk Scorecard: understanding recalibration fundamentals, log-odds graphs, quarterly realignments, and the interplay between slope and intercept via Rotation and Translation.
- Direct Integration of Macroeconomic Variables: using macroeconomic indicators as direct inputs in logistic regression-based scorecards and assessing their implicit recalibration effects.
- Challenges and Considerations: addressing regulatory constraints, data limitations, and the impact of unforeseen events like the COVID-19 pandemic.
Benefits of attending
This workshop will provide valuable insights to the credit risk and control community by:
- Equipping participants with a structured framework for integrating macroeconomic variables into credit risk models.
- Clarifying the advantages and limitations of various modelling approaches through empirical examples and visualization techniques.
- Enhancing the ability to navigate data challenges and regulatory scrutiny in IRB-approved models.
Who should attend?
- Credit risk modellers and analysts
- Financial and regulatory professionals
- Data scientists in risk management
- Professionals involved in credit scoring and model validation
Format
The session will be interactive with questions and discussions at various points.
Presenter and Bio
Luke Stanislaus, Risk Analyst Lead, Nationwide Building Society
Luke Stanislaus is a Risk Analyst at Nationwide Building Society. He is a Mathematics graduate from the University of Warwick and has been part of the Secured Internal Ratings Based (IRB) team at Nationwide since January 2024. His work has focused on expanding Credit Concentration models and exploring the integration of macroeconomic variables into credit risk modelling. Drawing from this experience, Luke will offer a first-principles perspective on Credit Risk, informed by the challenges and insights he has encountered.
He can be reached via LinkedIn.