---
title: Predictive Performance in Credit Scoring
url: https://www.ml-quant.com/papers/ssrn/4492913/
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 4492913
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4492913
featured: 2023-07-05
citations: unknown
topic: Risk, Credit & Banking
---


# Predictive Performance in Credit Scoring

XPER method breaks down machine learning model performance to identify impactful features.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4492913
- Identifier: SSRN 4492913
- Released: 2022-11-22
- First featured: Quant Letter No. 6 (2023-07-05): https://www.ml-quant.com/issues/2023-07-05/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Risk, Credit & Banking

## Related

- [Calibrating Distribution Models from PELVE](https://www.ml-quant.com/papers/arxiv/2204.08882/): PELVE converts VaR to ES and provides insights on distribution models for insurance.
- [Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learning](https://www.ml-quant.com/papers/arxiv/2306.15585/): Reinforcement learning techniques automate optimal credit card limit adjustments, outperforming other strategies.
- [Machine Learning-Based Variable Selection for Clustered Credit Risk Modeling](https://www.ml-quant.com/papers/ssrn/4506537/): The piece proposes a machine learning-based method for selecting variables in clustered credit risk modeling, using the most influential risk drivers as clustering variables.
- [Interbank Decisions and Margins of Stability: an Agent-Based Stock-Flow Consistent Approach](https://www.ml-quant.com/papers/arxiv/2306.05860/): Banks' refusal to roll over short-term interbank liabilities can compromise the efficiency of the interbank market and reduce the effectiveness of conventional monetary policies.
- [Multimodal Document Analytics for Banking Process Automation](https://www.ml-quant.com/papers/arxiv/2307.11845/): The research investigates the use of advanced document analytics, such as LayoutXLM, in banking to analyze diverse documents efficiently and accurately, enhancing operational efficiency.
- [Double free boundary problem for defaultable corporate bond with credit rating migration risks and their asymptotic behaviors](https://www.ml-quant.com/papers/arxiv/2301.10898/): The paper presents a pricing model for a corporate bond with credit rating migration risk, proving the solution's existence, uniqueness, and regularity.