--- title: Risk, Credit & Banking url: https://www.ml-quant.com/topics/risk-credit-banking/ site: ML-Quant (https://www.ml-quant.com) updated: 2026-10-09 license: Summaries CC BY 4.0; links go to the original sources index: https://www.ml-quant.com/llms.txt --- # Risk, Credit & Banking Credit risk, default prediction, banking, systemic risk and risk measures. 381 papers featured; 58 in the last 12 months. Papers featured per quarter: 2023 Q2 17, 2023 Q3 32, 2023 Q4 31, 2024 Q1 22, 2024 Q2 51, 2024 Q3 44, 2024 Q4 34, 2025 Q1 41, 2025 Q2 43, 2025 Q3 7, 2025 Q4 18, 2026 Q1 0, 2026 Q2 3, 2026 Q3 20, 2026 Q4 18 ## Most cited - [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://www.ml-quant.com/papers/arxiv/2402.00299/): 50 citations. A dynamic multilayer network model has been created for improved credit risk assessment, considering borrower connections and their evolution over time. - [Moderating effects of gender and family responsibilities on the relations between work–family policies and job performance](https://www.ml-quant.com/papers/doi/10-1080-09585192-2018-1505762/): 28 citations. Research on the Spanish banking sector shows that work-family policies indirectly improve job performance through generated well-being, with no significant influence from gender or family responsibilities. - [Machine Learning Based Risk Assessment for Financial Management in Big Data IoT Credit](https://www.ml-quant.com/papers/ssrn/5086671/): 27 citations. The article highlights the importance of machine learning in evaluating financial management in big data and IoT in the credit industry, improving creditworthiness accuracy. - [Failing Banks](https://www.ml-quant.com/papers/arxiv/2506.06082/): 19 citations. A study reveals that US bank failures from 1863 to 2024 are mainly due to worsening bank fundamentals like increasing asset losses and reliance on costly noncore funding. - [Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts](https://www.ml-quant.com/papers/arxiv/2503.18029/): 19 citations. The study shows that using AI language model, ChatGPT, in lending decisions can improve credit default predictions and increase profitability in finance. - [Explainable Automated Machine Learning for Credit Decisions: Enhancing Human Artificial Intelligence Collaboration in Financial Engineering](https://www.ml-quant.com/papers/arxiv/2402.03806/): 19 citations. The use of Explainable Automated Machine Learning (AutoML) in financial engineering can improve the development of machine learning models for credit scoring and increase transparency in AI financial decisions. - [Contagion Effects of the Silicon Valley Bank Run](https://www.ml-quant.com/papers/arxiv/2308.06642/): 19 citations. The study analyzes the impact of Silicon Valley Bank's failure on other banks, highlighting the role of uninsured deposits and bank size, with mid-sized banks being most affected. - [Model Aggregation for Risk Evaluation and Robust Optimization](https://www.ml-quant.com/papers/arxiv/2201.06370/): 17 citations. The model aggregation (MA) approach is a new method for risk evaluation that provides a robust value and distributional model, refining Value-at-Risk and Expected Shortfall characterizations. - [Neural Networks for Insurance Pricing with Frequency and Severity Data: A Benchmark Study from Data Preprocessing to Technical Tariff](https://www.ml-quant.com/papers/doi/10-1080-10920277-2025-2451860/): 16 citations. The article discusses the application of deep learning in insurance pricing, comparing different models and offering a method to interpret neural network insights through generalized linear models. - [Infinite-mean models in risk management: Discussions and recent advances](https://www.ml-quant.com/papers/arxiv/2408.08678/): 16 citations. The article explores the importance and challenges of using infinite-mean models in economics and finance, particularly when dealing with heavy-tailed datasets. - [Comparative Evaluation of Anomaly Detection Methods for Fraud Detection in Online Credit Card Payments](https://www.ml-quant.com/papers/arxiv/2312.13896/): 16 citations. A study found that LightGBM was the best for fraud detection when comparing anomaly detection and standard supervised learning methods, but it was more susceptible to distribution shifts, questioning the advantage of combining these two methods. - [Law-invariant return and star-shaped risk measures](https://www.ml-quant.com/papers/arxiv/2310.19552/): 16 citations. The paper introduces new characterizations for law-invariant star-shaped functionals, demonstrating their wide use in finance, insurance, and probability scenarios. ## Latest - [Agentic AI Systems and Financial Stability, From Model Risk to Systemic Risk](https://www.ml-quant.com/papers/arxiv/2610.08806/) (2026-10-09): The study shows that agentic AI systems sharing a foundation model create non-diversifiable common exposure whose systemic risk floor does not shrink as the fleet grows, shifting concern from individual model risk to population-level contagion. - [Ranking Prior Alignment for Credit Risk Modeling: When Do External Priors Matter?](https://www.ml-quant.com/papers/arxiv/2610.11146/) (2026-10-09): A model-agnostic framework distills ranking priors from experts or teacher models into credit scorers via KL divergence, improving cold-start performance with scarce labeled data. - [Regime-Aware Estimation of Large Equity Correlation Matrices: Tail-Pairwise Dependence and Dynamic Conditional Correlation Decomposition for Water and Energy Sectors](https://www.ml-quant.com/papers/arxiv/2610.12166/) (2026-10-09): Fitting separate dependence matrices to lower-tail, central, and upper-tail regimes reveals tail-driven co-movements that single Gaussian-copula structures systematically miss. - [Heterogeneous Estimation of the Causal Effect of Debt Restructuring Interventions: A Causal and Explainable Uplift Modeling Framework for the Economic Optimization of Credit Risk Portfolios](https://www.ml-quant.com/papers/ssrn/7556744/) (2026-10-09): A causal framework compares six estimators of treatment effect to optimally assign debt restructuring interventions, revealing that targeting borrowers by predicted effect generates substantially positive value where blanket treatment fails. - [Common Banks, Supply Chains, and the Transmission of Real Shocks](https://www.ml-quant.com/papers/ssrn/7588198/) (2026-10-09): Using Portuguese wildfire data, the research finds firms whose banks also lend to suppliers experience 10 percentage points smaller credit declines and face attenuated real losses. - [Beyond Financial Conditions: Measuring Structural Vulnerabilities in the U.S. Financial System](https://www.ml-quant.com/papers/repec/fip-fedgfe-103791/) (2026-10-09): An index capturing structural financial weaknesses displays gradual buildup before crises, predicts shock amplification, and reveals delayed monetary policy transmission effects. - [The Equilibrium Impact of Credit Frictions: Evidence from Default Risk Using Firm-Level Data](https://www.ml-quant.com/papers/repec/nbr-nberwo-35552/) (2026-10-09): UK firm-level data shows relaxing credit frictions raises output by 25% and wages by 23%, with most gains from capital accumulation rather than reallocation. - [What is the Impact of a Major Unconventional Monetary Policy Intervention?](https://www.ml-quant.com/papers/repec/bdm-wpaper-2026-01/) (2026-10-09): The ECB's "whatever it takes" announcement reversed euro area banks' risk appetite, reducing loan growth and credit risk, showing capitalization can curb lending during crises. - [Bankers’ Outside Options and Financial Risk](https://www.ml-quant.com/papers/repec/ajk-ajkdps-429/) (2026-10-09): Improved job opportunities for bankers increase non-investment-grade lending and borrower risk without compensating spreads, raising systemic risk through weakened workplace discipline. - [Banks versus Private Credit: How Capital Requirements Shape Tailored Lending](https://www.ml-quant.com/papers/ssrn/7524779/) (2026-10-02): The study models how capital requirements tax banks on tailored loans, pushing riskier firms toward private credit; evidence shows that tighter leverage rules reduce bank tailoring by 25 percent in quantitative terms. - [The Geometry of Risk: An Integrated Monitoring Framework for Multi-Asset Systemic Stress](https://www.ml-quant.com/papers/ssrn/7521018/) (2026-10-02): The research develops a four-layer diagnostic framework combining network topology, dynamic causality, tail risk, and regime classification to monitor multi-asset systemic stress in real time. - [Impact of Central Bank Digital Currencies on Financial Stability](https://www.ml-quant.com/papers/ssrn/7540719/) (2026-10-02): Calibrated simulations show existing central bank digital currencies remain below thresholds needed to measurably affect bank credit or financial stability. - [The Fed Put and Bank Risk-Taking: Evidence from the Loan Book](https://www.ml-quant.com/papers/repec/ces-ceswps-12980/) (2026-10-02): The paper shows that monetary policy reduces perceived tail risk for bank equity, encouraging banks to originate riskier loans to commercial and industrial borrowers. - [Bank Dollarization, Lending Behavior and Real Effects](https://www.ml-quant.com/papers/repec/tcb-wpaper-2617/) (2026-10-02): The study shows that banks with high foreign exchange risk reduce lending to both exposed and unexposed firms after exchange rate shocks, with measurable real effects on small and medium enterprises. - [Financial frictions and firms’ capital composition: a structural estimation of firms’ borrowing constraints for the UK](https://www.ml-quant.com/papers/repec/boe-boeewp-023254/) (2026-10-02): UK firm-level analysis shows that interest rate spreads are less sensitive to capital-to-debt ratios for firms with higher intangible intensity, suggesting intangibles are less effective collateral than tangible assets. - [Solvency and systemic risk of European life insurers](https://www.ml-quant.com/papers/repec/boe-boeewp-023290/) (2026-10-02): The research distinguishes solvency risk from systemic risk in European life insurers, finding growing systemic risk exposure since 2007 and evidence of interconnectedness with banks that intensifies during financial stress. - [Financial Crisis Cycles](https://www.ml-quant.com/papers/repec/cnn-wpaper-26-015e/) (2026-10-02): A theoretical model shows that debt accumulation during booms delays post-crash recovery through debt overhang and coordination failures, with debt restructuring conditional on recapitalization being more efficient than unconditional subsidies. - [The Cov-lite Liquidity Advantage, Regulatory Pressures, and the Evolution of the Leveraged Loan Market](https://www.ml-quant.com/papers/repec/nbr-nberwo-35617/) (2026-10-02): Post-GFC, banks facing stricter regulation increased cov-lite loan issuances due to liquidity advantages that lower credit spreads, particularly for private firms seeking easier asset sales. - [Financial Tail Risk Beyond Lipschitz Continuity via Semi-Discrete Optimal Transport](https://www.ml-quant.com/papers/arxiv/2609.27785/) (2026-09-25): Proposes semi-discrete optimal transport to capture heavy tails in financial returns, maintaining stable tail ratio estimates across diverse neural generators when standard Lipschitz methods fail. - [DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks](https://www.ml-quant.com/papers/arxiv/2609.25542/) (2026-09-25): A dual-perspective graph neural network framework predicts corporate defaults from buyer-seller transaction networks, improving approval rates by 7-11 percentage points without increasing default risk. - [Risk Measures under Paired-Ambiguity: A Deep Learning Reflected BSDE Framework](https://www.ml-quant.com/papers/arxiv/2609.23768/) (2026-09-25): Develops a deep learning scheme for optimal stopping under simultaneous model and discount-rate ambiguity, with application to American option valuation under uncertainty. - [Forward Guidance and the Dynamics of Bank Credit: The Bank Balance-Sheet Channel of Monetary News](https://www.ml-quant.com/papers/ssrn/7514178/) (2026-09-25): High-frequency analysis reveals contractionary forward guidance immediately cuts bank lending, while expansionary guidance produces weak stimulus, driven by binding capital constraints. - [Monetary policy transmission by securitising banks](https://www.ml-quant.com/papers/ssrn/7515879/) (2026-09-25): Banks engaged in securitization contract lending more sharply after monetary tightening because their investor base demands higher returns and cuts risk exposure when rates rise. - [Hedge Fund Performance and Interest Rate Conditions: Evidence from Regulatory Data](https://www.ml-quant.com/papers/ssrn/7493702/) (2026-09-25): Using SEC filings from 2013-2021, the paper finds hedge fund returns show heterogeneous sensitivity to interest rates, with effects varying by strategy, leverage, and derivative exposure. - [State-dependent global banking systemic risk: An integrated framework of network connectedness, tail risk, and global financial conditions](https://www.ml-quant.com/papers/ssrn/7493706/) (2026-09-25): Combining quantile-connectedness, tail-risk measures, and network analysis, the research shows tail connectedness exceeds median levels and lower-tail effects persist longer, with the VIX alone reliably predicting next-week systemic risk. - [The Low Return Channel of Negative Interest Rates in Bank Lending](https://www.ml-quant.com/papers/ssrn/7489554/) (2026-09-25): Japan's 2016 negative-rate policy reduced lending from low-profitability banks holding reserves, consistent with lower expected returns on bank assets rather than deposit-side stress. - [Signature-Based Structural Models and Applications in Credit Markets](https://www.ml-quant.com/papers/ssrn/7498599/) (2026-09-25): The study develops a time-varying signature asset model for structural credit that improves calibration across CDS maturities and equity option prices, especially for high-yield firms. - [Sell, Hold Out, or Accept: The Creditor's Trilemma in Distressed Debt Exchanges](https://www.ml-quant.com/papers/ssrn/7502204/) (2026-09-25): Analysis of 284 distressed exchanges from 2009-2022 reveals over 50% of firms face subsequent default, with large illiquid creditors trapped in a prisoner's dilemma explaining high acceptance rates. - [The Global Credit Cycle](https://www.ml-quant.com/papers/repec/cpr-ceprdp-21268/) (2026-09-25): A nonlinear factor constructed from credit spreads and equity volatility prices global corporate bond returns, explaining up to 13% of three-month-ahead return variation across markets. - [The credit channel of monetary policy: direct survey evidence from UK firms](https://www.ml-quant.com/papers/repec/boe-boeewp-023260/) (2026-09-25): UK firm survey data validates that external borrowers face larger cost-of-capital increases and cut investment more than internal funders when rates rise, accounting for a quarter of monetary policy's total effect.