Artificial Intelligence and Credit Risk The Use of Alternative Data and Methods in Internal Credit Rating

Artificial Intelligence and Credit Risk The Use of Alternative Data and Methods in Internal Credit Rating

Weitere Versionen anzeigen (2)
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Locatelli, Rossella (VerfasserIn)
Format: Elektronisch E-Book
Sprache:English
Veröffentlicht: Cham Springer International Publishing AG 2022
Ausgabe:1st ed
Schlagworte:
Risk management
Credit-Management
Artificial intelligence
Online-Zugang:DE-2070s
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Intro
  • About This Book
  • Executive Summary (English)
  • Contents
  • About the Authors
  • List of Figures
  • List of Tables
  • 1 Introduction
  • 2 How AI Models Are Built
  • 2.1 Processing of Unstructured Data in AI Models
  • 2.1.1 The Main Structuring Techniques for "Unstructured" Data Are Text Analysis and Natural Language Processing
  • 2.1.2 What Does "Alternative Credit Data" Mean?
  • 2.2 Stand-Alone AI Models
  • 2.2.1 Decision Trees
  • 2.2.2 Random Forests
  • 2.2.3 Gradient Boosting
  • 2.2.4 Neural Networks
  • 2.2.5 Autoencoder, a Special Type of Neural Network
  • References
  • 3 AI Tools in Credit Risk
  • 3.1 Use of Alternative Techniques and Data in Probability of Default Models
  • 3.1.1 The Type of Data Analysed and How They Are Managed
  • 3.1.2 The Interpretability of Results: An Important Factor
  • 3.1.3 A Practical Case: Risk Discrimination for Borrowers with Seasonal Businesses
  • 3.1.4 A Practical Case: Identification of Counterparty Risk During the COVID-19 Crisis
  • 3.1.5 A Practical Case: Early Warnings
  • 3.1.6 A Practical Case: Advanced Analytics in Loan Approval
  • 3.2 How to Improve Traditional Models Using AI Techniques
  • 3.2.1 A Practical Application: The Two-Step Approach
  • 3.2.2 The Estimation Methodology Adopted
  • 3.3 Applying an AI Model to Asset Management
  • 3.4 Use of AI Models for the Validation/Benchmarking of Traditional Models
  • 3.4.1 ML Techniques for Benchmarking Capital Requirements Models
  • 3.4.2 Initial Applications for Management Purposes
  • References
  • 4 The Validation of AI Techniques
  • 4.1 Possible Comparison Criteria Between Traditional Models and AI Models
  • 4.1.1 Principle 1: Accuracy
  • 4.1.2 Principle 2: Robustness
  • 4.1.3 Principle 3: Fairness
  • 4.1.4 Principle 4: Efficiency
  • 4.1.5 Principle 5: Explainability
  • 4.2 Interpretability and Stability of the Models' Outcomes
  • 4.2.1 Main Legislation
  • 4.2.2 Interpretability Methodological Notes
  • 4.2.3 Key Methodologies
  • 4.2.4 Focus Points
  • 4.2.5 Stability Methodological Notes
  • References
  • 5 Possible Evolutions in AI Models
  • 5.1 The Role of AI Models in the Credit Risk of Tomorrow
  • 5.2 Ethics and Transparency of Results
  • 5.2.1 Privacy
  • 5.2.2 Transparency
  • 5.2.3 Discrimination
  • 5.2.4 Inclusion
  • References
  • Appendix
  • Glossary
  • Bibliography
  • Index

Ähnliche Einträge