Written by students who passed Immediately available after payment Read online or as PDF Wrong document? Swap it for free 4.6 TrustPilot
logo-home
Document preview thumbnail
Preview 1 out of 3 pages
Summary

Summary Guest Lecture Notes | Machine Learning & Financial Supervision | Tilburg University | 2026/27

Document preview thumbnail
Preview 1 out of 3 pages

Guest lecture notes from DNB Project Manager Juul van de Bracht on machine learning applications in financial supervision, covering the Strategy Analytics course at Tilburg University. Topics include DNB's five core tasks, financial supervision fundamentals, the ATM model, machine learning techniques (Random Forest, XGBoost, SVM), AI regulation, and three case studies on ML in supervision, supervision of ML/AI, and outlier detection in pension funds. Essential for understanding how data analytics and machine learning are transforming financial oversight and risk assessment in practice.

Content preview

GUEST LECTURE

- Juul van de Bracht – Project Manager & data analyst at DNB
- DNB five core tasks
o Solid financial institutions
o Stable prices
o Reliable payments systems
o Statistics, analysis and advice
o Responding appropriately to financial institutions in distress
- How we serve the public interest
o Financial education
§ Teaching materials for schools
§ Public information
§ Social media presence
§ De nieuwe schatkamer
- What is the TP (pension supervision/toezicht persioen) and TMO (transition management office) and
WTP (wet toekomst pensioenen/law future pension)
- How is the WTP-transition progressing
o Now 6 funds have switched, 20 more will
o This month, more than 50% of all participants will be in the new system
o Remaining will transist in 2027 and 28
- Basics of supervising
o What is financial supervision
§ Monitoring banks, insurers, financial institutions if safely and fairly
§ Supervisors like DNB, AFM, ACM, SSM, ECB
§ Goal = maintain trust in financial system and prevent crises
o How does data help in supervision
§ Rely on data to understand and monitor risks at financial institutions
§ Spot trends
§ DNB uses ATM to process more data-driven and risk-based
§ ATM models automatically assess risks
• Quantitative data gives objective , comparable insights
• Qualitative data adds context and helps explain the numbers
- ATM is based on rule-based models
o Risks are assessed with fixed formulas and complex calculations
o Benefit = rule-based and calculation-based models are transparent and easy to follow and
explain
- What could machine learning models do in ATM models
o Machine learning finds patterns in large datasets that supervisors might miss
o Techniques: random forest, XGBoost, SVM
§ Variables
• Liquidity = the inability to meet unexpected financial obligations
• Interest rate = changes in the financial position due to changes in the risk-
free interest rate structure

Document information

Study
Uploaded on
August 10, 2026
Number of pages
3
Written in
2025/2026
Type
Summary
$5.06

Wrong document? Swap it for free Within 14 days of purchase and before downloading, you can choose a different document. You can simply spend the amount again.
Written by students who passed
Immediately available after payment
Read online or as PDF

Sold
1
Followers
0
Items
11
Last sold
11 months ago


Why students choose Stuvia

Created by fellow students, verified by reviews

Quality you can trust: written by students who passed their tests and reviewed by others who've used these notes.

Didn't get what you expected? Choose another document

No worries! You can instantly pick a different document that better fits what you're looking for.

Pay as you like, start learning right away

No subscription, no commitments. Pay the way you're used to via credit card and download your PDF document instantly.

Student with book image

“Bought, downloaded, and aced it. It really can be that simple.”

Alisha Student

Working on your references?

Create accurate citations in APA, MLA and Harvard with our free citation generator.

Working on your references?

Frequently asked questions