---
title: Credit Risk Modeling
url: https://www.ml-quant.com/papers/ssrn/5093887/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 5093887
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5093887
featured: 2025-01-15
citations: unknown
topic: Risk, Credit & Banking
---


# Credit Risk Modeling

The article discusses the use of normalizing flows and invertible neural networks in credit risk modeling to enhance default time estimation and portfolio risk assessment.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5093887
- Identifier: SSRN 5093887
- Released: 2025-01-11
- First featured: Quant Letter No. 82 (2025-01-15): https://www.ml-quant.com/issues/2025-01-15/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Risk, Credit & Banking

## Related

- [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://www.ml-quant.com/papers/arxiv/2402.00299/): A dynamic multilayer network model has been created for improved credit risk assessment, considering borrower connections and their evolution over time.
- [An Explicit Scheme for Pathwise XVA Computations](https://www.ml-quant.com/papers/arxiv/2401.13314/): A new simulation/regression scheme for a type of anticipated BSDEs is introduced, using neural network least-squares and quantile regressions, showing better results in high-dimensional and hybrid market/default risks XVA use-case.
- [Study on Intelligent Forecasting of Credit Bond Default Risk](https://www.ml-quant.com/papers/arxiv/2305.12142/): Intelligent forecasting framework for default risk in China's bond market using ConvLSTM neural network.
- [Artificial Neural Networks Enhance Credit Risk Prediction](https://www.ml-quant.com/papers/repec/taf-oaefxx-v-11-y-2023-i-1-p-2210916/): The study reveals that machine learning is superior to logistic regression in predicting company bankruptcy, and its predictive accuracy increases when factors like changes in operating expenditure are included in the model.
- [Convolutional Neural Network for Enterprise Default Risk Prediction](https://www.ml-quant.com/papers/repec/hin-complx-5139562/): The study proposes a comprehensive metric model to address imbalanced datasets and redundant features in machine learning models for default risk prediction.
- [Interpretable Learning in Credit Risk](https://www.ml-quant.com/papers/repec/eee-riibaf-v-65-y-2023-i-c-s0275531923000661/): Neural network with selective interpretability introduced for credit risk assessment, shallow model leads to better accuracy for specific data portions.