Μη εξυπηρετούμενα δάνεια : κανονιστικό πλαίσιο επιτήρησης και ποσοτικές τεχνικές εκτίμησης κινδύνων

Τσαρούχης, Δημήτριος

Non-performing loans : supervisory regulatory framework and quantitative risk assessment techniques

Master Thesis

Author

Τσαρούχης, Δημήτριος

Date

2025-09

Abstract

In a banking system, the loan portfolio plays a central role in the business strategy of credit institutions as it represents their primary source of income. At the same time, it is linked to credit risk, which arises when the borrower is unable to repay the loan or delays repayment according to the terms of the agreement. The ratio of non-performing loans to total loans, as a proportion of total loans, is a critical factor in defining credit risk, and at the same time, it is one of the most important factors contributing to the systemic insolvency of the banking sector, hindering the development of both the banking system and the economy in general. The Basel II regulatory framework allows financial institutions to use Internal – Rating based approaches to calculate the capital they need to maintain to address potential losses from their loan portfolios. The aim of this thesis is to approach the credit risk inherent in each credit, including overdue loans, provisions for doubtful claims, and risk assessment. This thesis is structured into five chapters. The first chapter presents the framework for the capital adequacy of credit institutions (Basel I, II, III) and the calculation of required capital with two proposed approaches: the Standardized Approach and the Internal – Rating based Approach. The second chapter discusses the concept of non-performing loans and the factors that affect them. It explores the macroeconomic environment of our country, examining the relationship between non – performing loans and macroeconomic factors, and presents statistical data from the Bank of Greece regarding the evolution of loan balances and delinquencies for all Greek banks from 2002 to June 2024. In the third chapter, reference is made to credit risk assessment models and their characteristics, the specifications they must meet in order to be effective, as well as the process followed for their development. Furthermore, the main credit scoring models and the techniques used for their validation are presented in detail. In the fourth chapter, credit scoring models are developed based on the techniques of logistic regression, discriminant analysis, and decision trees, using real-world data. Finally, in the fifth chapter, a summary of the study is provided.

Postgraduate Studies Programme

Αναλογιστική Επιστήμη και Διαχείριση Κινδύνων

Department

Σχολή Χρηματοοικονομικής και Στατιστικής. Τμήμα Στατιστικής και Ασφαλιστικής Επιστήμης

Number of pages

150

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/18218

Collections

Τμήμα Στατιστικής και Ασφαλιστικής Επιστήμης

Show full item record

Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα