Opening the black box : quantile neural networks for loss given default prediction
Year of publication: |
2022
|
---|---|
Authors: | Kellner, Ralf ; Nagl, Maximilian ; Rösch, Daniel |
Published in: |
Journal of banking & finance. - Amsterdam [u.a.] : Elsevier, ISSN 0378-4266, ZDB-ID 752905-3. - Vol. 134.2022, p. 1-20
|
Subject: | Black box | Explainable machine learning | Global credit data | Neural networks | Quantile regression | Neuronale Netze | Prognoseverfahren | Forecasting model | Regressionsanalyse | Regression analysis | Künstliche Intelligenz | Artificial intelligence | Kreditrisiko | Credit risk | Kreditwürdigkeit | Credit rating | Theorie | Theory | Schätzung | Estimation |
-
El Khair Ghoujdam, Mousaab, (2024)
-
Prediction of corporate credit ratings with machine learning : simple interpretative models
Galil, Koresh, (2023)
-
A deep learning approach to estimate forward default intensities
Divernois, Marc-Aurèle, (2020)
- More ...
-
Statistical and machine learning for credit and market risk management
Nagl, Maximilian, (2022)
-
Time varying dependences between real estate crypto, real estate and crypto returns
Nagl, Cathrine, (2024)
-
Deep Calibration of Financial Models : Turning Theory Into Practice
Büchel, Patrick, (2020)
- More ...