Research Affiliates

Dr. María Óskarsdóttir
Lecturer of Mathematical Modelling, University of Southampton

Professor Stefan Lessmann
Professor of Information Systems at Humboldt-Universität zu Berlin

Professor Wouter Verbeke
Professor of Decision Science at KU Leuven
Resource Repository Contributors
The Credit Research Centre is proud to present a repository dedicated to resources provided by members of the credit & risk modelling community. We believe these resources to be practically useful and academically interesting.
We are currently growing our resource base. We are striving to include authors from diverse backgrounds, including academia, industry, and financial research institutions, ensuring a rich variety of perspectives and knowledge.

Denis Burakov
Senior Risk Manager – Data Science
Topics: Gradient Boosting, Logistic Regression / Neural Networks
Background
Denis specializes in risk management and AI/ML model development, with extensive experience in leading data science and analytics teams and managing complex advanced analytics projects in financial services. Over his career, Denis has worked in the risk departments of renowned organizations such as KPMG, N26, and most recently, Amazon, bringing a wealth of knowledge in developing and implementing advanced analytics solutions at the enterprise level. Denis's current expertise focuses on ML engineering and cloud AI applications for retail risk management tasks.
Professional Experience
Currently, Denis serves as a Senior Risk Manager at Amazon, where he develops predictive models and algorithms to optimize business processes using advanced ML techniques and emerging AI technology. Prior to Amazon, Denis enhanced N26's unsecured lending business by designing and implementing second-generation ML credit risk models, leading a team of data scientists and other analytical talent and managing partnerships with Germany’s top credit bureaus. At KPMG, Denis provided management consulting for major European financial services providers, enhancing their risk management strategies with his expertise in advanced analytics, regulatory compliance, and applied model development.
Research Interests
- Credit Risk Modeling and Validation
- ML Modeling Approaches (Gradient Boosting, Neural Networks)
- Theory of Maximum Likelihood Estimation
- Data Science Education and Training
Recent Publications
"Beyond Credit Scoring: A Decision-Making Framework for Profitable Lending," Taktile, 2024.
“Machine Learning in IRB: Challenges and Opportunities”. Presented at Credit Risk Management for Banking & Financial Sector, May 2024, Berlin.

Dr Joseph L. Breeden
CEO – Deep Future Analytics LLC
President – Model Risk Managers’ International Assocation
Topics: Age Period Cohort Modelling
Background
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 Assocation.
Dr. Breeden invented vintage analytics for lending in 1997 and created credit risk models through the 1995 Mexican Peso Crisis, the 1997 Asian Economic Crisis, the 2001 Global Recession, the 2003 Hong Kong SARS Recession, the 2007-2009 US Mortgage Crisis and Global Financial Crisis, and the COVID-19 Pandemic. These crises 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 modeling, combining vintage analytics with behavior scoring using logistic regression or machine learning.
Qualifications
Dr. Breeden earned separate B.S. degrees in mathematics and physics (Indiana University), and a Ph.D. in physics (University of Illinois, Urbana-Champaign). He 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.
Research Interests
- Credit risk analytics for loans and deposits with focus on integrating analytics across business functions
- Climate risk stress testing and model validation
- AI ethics, including monitoring AI systems for regulatory and ethical compliance
- Analytics of wine auction prices
- Using chaos theory in interstellar travel
Recent Publications
- Breeden, J.L., “Impacts of Drought on Loan Repayment”, Journal of Risk and Financial Management, 16:85, 2023.
- Breeden, J.L., Y. Leonova, and A. Bellotti, “Instabilities using Cox PH for forecasting or stress testing loan portfolios”, Journal of Credit Risk, 2023.
- Breeden, J.L. and Y. Leonova, “Macroeconomic Adverse Selection in Machine Learning Models of Credit Risk”, ITISE, Grand Canary Island, 2023, Engineering Proceedings, 38:95—106
- Breeden, J.L. and Y. Leonova, “Stabilizing Machine Learning Models with Age-Period-Cohort Inputs for Scoring and Stress Testing”, Frontiers in Applied Mathematics and Statistics, 2023.
- Breeden, J.L., “An Age-Period-Cohort Framework for Profit and Profit Volatility Modeling”, J of Mathematics, 12:1427, 2024
- Breeden, J.L., “Do Heterogenous or Homogenous Wine Lots Result in the Highest Auction Prices?”, International Journal of Wine Business Research, August, 2023.
- Breeden, J.L., “Scoring AI Policy Recommendations with Risk-Adjusted Gain in Net Present Happiness”, AI and Ethics, 16 October 2023.
- Breeden, J.L., “The Evolution of Goals in AI Agents”AI and Ethics, 2025.
- Breeden, J.L. “Normalizing Pandemic Data for Credit Scoring”, May 2025

Dr Andrija Djurovic
Risk Advisory – Deloitte
Topics: Concentration Risk
Background
Andrija is a seasoned credit risk professional with over ten years of experience in credit risk modeling and more than fifteen years in data analytics. He has worked across various industries, including official statistics, banking, and telecommunications. Throughout his career, Andrija has collaborated with notable organizations such as Deloitte, Société Générale, Hypo Alpe-Adria Group, and Telenor. He is currently serving as an external consultant for Deloitte Sweden.
Most of his professional journey has taken place in multicultural environments across several countries, including Montenegro, Luxembourg, Austria, Romania, and Sweden. He also has practical academic experience, having served as a teaching assistant in statistics at several universities.
His expertise includes modeling Probability of Default, Loss Given Default, and Exposure at Default, as well as developing scoring models, macroeconomic models, and conducting comprehensive portfolio analysis. Working within key frameworks such as IRB, IFRS 9, and stress testing, Andrija has a deep understanding of the regulatory landscape. Drawing on a strong statistical background that bridges academia and industry, he excels at developing tailored analytical solutions to meet specific business needs. Notably, Andrija is the author and developer of essential
R
packages tailored for credit risk modeling:
monobin,
monobinShiny,
PDtoolkit,
LGDtoolkit
as well as the
Python
package:
Research Interests
- Credit Risk Modeling
- Applied Statistics
- Machine Learning
- Software Engineering
- Educating on Banking Model Best Practices
Recent Publications
- Djurovic, Andrija. (2025). Credit Risk Modeling Working Notes: A Collection of Presentations, Experiments, and Technical Papers .
- Djurovic, Andrija. (2024). Applied Data Science for Credit Risk: A Practical Guide in R and Python
- Djurovic, Andrija. (2023). Probability of Default Rating Modeling with R: Comprehensive overview of the modeling processes, principles, and designs