Instructional goals
To equip students with the conceptual framework and analytical tools, including AI techniques, that will enable them to assess the creditworthiness of non-financial firms and produce their ratings, covering also emerging risk sources
Prerequisites
Corporate finance, financial statement analysis, basic macroeconomics, basic statistics and econometrics, some knowledge of R, basic machine learning
Intended learning outcomes
To enable students to successfully apply for roles in banks, rating agencies, and private capital firms—specifically as Credit risk analysts, Quantitative analysts, and Risk model developers—and to strengthen their preparation towards Analyst positions in Investment banking and Corporate finance departments
Course Contents
The course has two parts. Part 1 deals with: (i) the standard credit analysis of firms by means of financial ratios and credit performance variables, employing multivariate logistic regression and yielding the statistical rating; (ii) the expert analysis of other information and risk sources, leading to the full rating of the firm. Part 2 deals with new data types and AI applications including: machine learning for credit risk assessment, sentiment analysis with natural language processing, climate risk, social and governance risk, cyber risk
Reference Books
Antonio Scalia (ed.), Corporate credit analysis and AI, 2026, Springer
Teaching Methods
Standard lectures, applied sessions involving R code, case studies.
Experts and senior credit analysts will contribute to applied sessions and talks
Assessment Method
Active classroom participation, group work, and final exam.
Group work consists of credit risk assessment problems, including statistical analysis and estimation of the probability of default of a sample of firms by means of R.
Final exam is largely based on the lecture notes. It has multiple choice questions and open-ended questions.
Grade obtained in group work yields 1/3 of final grade.
Final written exam yields 2/3 of final grade
Thesis assignment criteria
Candidates should show a genuine interest and active participation throughout the course. They are normally expected to lead their group work and present the results.
Week 1
Introduction: objectives, contents, applications, professional uses, datasets, AI tools, R exercises, group work, exam.
Credit risk assessment models
Book chaps. 1-2, lecture notes (all weeks)
Week 2
Agency ratings, banks' IRB models, rating tools, central banks' in-house systems (ICAS)
Financial ratios, credit variables, Z-score model, logit model, credit behaviour model
Book chaps. 8-9
Week 3
Applied session 1: logit estimation of the financial model.
Applied session 2: credit performance variables, logit estimation of the credit performance model
Book chap. 3
Week 4
Applied session 3: Integration of financial model and credit performance model.
Applied session 4: model performance, backtesting, discriminatory and predictive power
Book chap. 3
Week 5
Credit risk analysis. Case study 1: the Bank of Italy’s ICAS.
ICAS performance and backtesting
Book chap. 3
Week 6
The macro model.
Expert analysis: risk profiles, weighting scheme.
Rating committee, case studies
Book chaps. 4-5
Week 7
Climate transition risk.
NGFS scenarios, climate physical risk
Book chaps. 12-13
Week 8
Applied session 5: tree-based models for corporate default prediction, including decision trees, random forests, and gradient boosting; theoretical foundations and implementation.
Applied session 6: model combination and stacking, theoretical background and links to modern credit risk systems
Book chap. 11
Week 9
Deep learning, natural language processing and explainable AI in credit risk; conceptual, operational, and regulatory issues.
Case study 2: LLM-based extraction of sentiment indicators from unstructured data and integration into credit risk models
Book chaps. 11, 15
Week 10
Case study 3: the climate risk survey.
Case study 4: S and G variables
Book chaps. 6, 14
Week 11
Case study 5: Cyber risk.
Case study 6: the rating of Italian firms, stylized facts
Book chaps. 16, 7
Week 12
Mock exam.
Review of selected topics and wrap up