20249 - CREDIT RISK MANAGEMENT
Department of Finance
Course taught in English
Go to class group/s: 31
ACME (6 credits - I sem. - OP | SECS-P/11) - AFM (6 credits - I sem. - OP | SECS-P/11) - AI (6 credits - I sem. - OP | SECS-P/11) - CLMG (6 credits - I sem. - OP | SECS-P/11) - DSBA (6 credits - I sem. - OP | SECS-P/11) - EMIT (6 credits - I sem. - OP | SECS-P/11) - ESS (6 credits - I sem. - OP | ECON-09/B | SECS-P/11) - FIN (6 credits - I sem. - OP | SECS-P/11) - GIO (6 credits - I sem. - OP | SECS-P/11) - IM (6 credits - I sem. - OP | SECS-P/11) - MM (6 credits - I sem. - OP | SECS-P/11) - PPA (6 credits - I sem. - OP | SECS-P/11)
Course Director:
GIACOMO DE LAURENTIS
GIACOMO DE LAURENTIS
Suggested background knowledge
No prerequisites are needed to attend the course
Mission & Content Summary
MISSION
Credit risk management is a rapidly evolving topic, key not only for bank management but also for other financial institutions and even for non-financial companies. In terms of regulatory capital absorbed, credit risk account for about 90% of total capital required for European banks. Opportunity and risks of leveraging on LLM, AI and machine learning in the different stages of data collection, model building, and model validation are today adding complexity to the standard regulatory and methodological issues credit risk departments confront. Banks, ECB and other authorities, insurance companies, non-bank financial institutions, and also non-financial corporations are today heavily recruiting graduates with good knowledge of the field.
CONTENT SUMMARY
- Introduction: concepts, methodologies and tools of credit risk management.
- Building statistical-based scoring systems of probability of default: definition of default to be used and its implications.
- Sampling, data mining and data transformations (Case study based on SPSS).
- Adding potential explanatory variables from Big Data by using LLM.
- Univariate analysis. Monotonicity, statistical requirements and predictive power of individual financial ratios (Case study based on SPSS).
- Transformations of financial ratios in order to maximize their predictive power (Case study based on SPSS).
- Models estimation (Case study based on SPSS).
- Models performance measurements, comparability of different models; from scorings to ratings: choosing cut-offs. Scoring calibration and rating quantification (Case study based on SPSS).
- Internal validation and regulatory validation. Quantitative and qualitative model validation; benchmarking.
- Regulatory guidelines for AI/machine learning usage in credit risk models.
- Credit risk measures taxonomy and their impacts on portfolio models structure
- Portfolio models and their relation with Basel capital adequacy rules.
- Credit risk pricing and risk adjusted performance measures. Internal data and market data.
Intended Learning Outcomes (ILO)
KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- get the state of the art of methodologies and practices of credit risk management in financial institutions, as well as in finance departments of large non-financial corporations.
- link risk measurement models and management policies in a comprehensive picture of key methodologies and tools that are currently under implementation in banks, non-financial institutions, and rating agencies. Both rating systems and portfolio models development stages will be considered, from both the methodological and regulatory perspectives.
APPLYING KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- Capitalizing on large real-world databases and statistical software tools such as IBM-SPSS, students will learn how to to build, to manage and to validate risk models, both statistical based rating systems and credit portfolio models.
Teaching methods
- Lectures
- Practical Exercises
- Collaborative Works / Assignments
DETAILS
The course provides a hands-on approach to credit risk models building and validation. This feature of the course is based on lectures, in-class exercises, incidents and case studies, both as individual or small-groups work. Almost each topic involves (class or home) exercises and incidents. A unique case study, based on a real world database of SMEs financial data, is used for building and validating a statistical based rating system during many class sessions; IBM-SPSS is used as statistical tool, because it is widely used in real world risk departments, because it is a quite friendly tool also for newcomers, and because the textbook published by Wiley is based on the same case study and IBM-SPSS applications. IBM-SPSS will be download on students laptop by Bocconi software help desk. A final group assignment is optional; each student in a group may earn from 0/30 to 2/30 additional points to those earned in the written exam. The final sessions of the course are taught by the Chief Risk Officer of an Italian bank, giving students direct exposure to the banking industry.
Assessment methods
| Continuous assessment | Partial exams | General exam | |
|---|---|---|---|
|
x | ||
|
x |
ATTENDING AND NOT ATTENDING STUDENTS
- A written exam based on three short essays tries to check the proper understanding of areas of credit risk management that have been covered in class. The final mark is expressed in thirties (X/30).
- A final group assignment is optional. Each student in a group may earn up to 2/30 additional points to those earned in the written exam; these additional points can be used up to the end of September 2027. The final group assignment is devoted to enhance not only how-to-do capabilities, but also team management, project management and (written) presentation skills.
Teaching materials
ATTENDING AND NOT ATTENDING STUDENTS
- DE LAURENTIS, MAINO, MOLTENI, Developing, Validating, and Using Internal Ratings. Methodologies and case studies, Wiley, 2010
- RENAULT DE SERVIGNY, Measuring and managing credit risk, McGraw-Hill 2004, (chapter 6).
- Slides sets, readings, SPSS print-outs and case studies (available on the course web site).
Last change 27/04/2026 12:48