Risks MDPI

🙌 #Publications2026 #FeaturePaper #LongevityRisk #DeRisking ✔️ Longevity Option and Longevity Swap De‑Risking Strategies Under Frailty‑Based Mortality Models ✍️ by Maria Carannante, Valeria D'Amato, Steven Haberman and Massimiliano Menzietti Does the choice of mortality model determine whether longevity risk transfer actually works? This study develops longevity option and swap de‑risking strategies based on frailty‑based mortality models to achieve more effective risk transfer through unbiased projections. The findings deliver a sobering message: when an appropriate de‑risking strategy is not selected, longevity risk transfer becomes ineffective—and the right strategy depends heavily on the underlying mortality model. 👉 https://brnw.ch/21x6s32 #FrailtyModels #MortalityModeling #RiskTransfer #PensionRisk #ActuarialScience #LifeExpectancy #Hedging #InsuranceRisk

🙌 #Publications2025 #FeaturePaper #EditorsChoice #VolatilityForecasting #MachineLearning ✔️ Historical Perspectives in Volatility Forecasting Methods with Machine Learning ✍️ by Zhiang Qiu, Clemens Kownatzki, Fabien Scalzo and Eun Sang Cha From implied volatility to Transformers—how has volatility forecasting evolved, and which methods actually hold up? This comprehensive survey traces the historical development of volatility models and benchmarks landmark approaches including GARCH, LSTM, and Transformer architectures. The authors open‑source their benchmark code to support further research—offering a valuable reference point for risk managers, option traders, and machine learning researchers navigating an ever‑expanding methodological landscape. 👉 https://brnw.ch/21x6x3M #RiskManagement #TimeSeriesAnalysis #DeepLearning #OptionPricing #StressTesting #FinancialInstitutions

🙌 #EditorsChoice #Publications2025 #CreditRisk #ExplainableAI - 12 October ✔️ Explainable Machine Learning Framework for Predicting Auto Loan Defaults ✍️ by Shengkun Xie and Tara Shingadia Can explainable AI make auto loan default prediction both accurate and transparent? This study compares Logistic Regression, Random Forest, XGBoost, and Stacked classifiers, integrating SHAP‑based feature selection with advanced resampling techniques (SMOTE, SMOTE‑Tomek, SMOTE‑ENN). The findings reveal that combining SHAP feature selection with SMOTE‑Tomek resampling and a Stacked Classifier consistently achieves superior predictive performance—highlighting the value of explainable AI in enhancing credit risk assessment for imbalanced financial datasets. 👉 https://brnw.ch/21x6kZk #MachineLearning #AutoLoans #LoanDefaults #PredictiveModeling #RiskAssessment #FinTech

🙌 #Publications2025 #EditorsChoice #highlycited #ESG #InvestmentEfficiency - 13 October ✔️ ESG Controversies and Firm Investment Efficiency: Impact and Mechanism Examination ✍️ by Shijin Ma, Fudan University and Tao Ma Do ESG controversies do more than damage reputations—do they actually impair how firms invest? Analyzing 847 Chinese A‑share listed companies (2007‑2022), this study finds ESG controversies significantly reduce investment efficiency by exacerbating agency costs and lowering audit quality. Notably, financing constraints and strong internal controls mitigate these negative effects. The impact is most pronounced for high‑pollution firms, non‑state‑owned enterprises, and those with lower digitalization—raising important questions about how ESG failures ripple through corporate decision‑making. 👉 https://brnw.ch/21x6mqS #ESG #InvestmentEfficiency #CorporateGovernance #FinancingConstraints #AShares #SustainableFinance #ESGControversies #Digitalization

🙌 #Publications2026 #FeaturePaper #EnterpriseRiskManagement #MachineLearning - 24 September ✔️ Enhancing Enterprise Risk Management and Internal Audit Practices by Applying Machine Learning Models ✍️ by Reneta Duhova, Angel Duhov, Petia Georgieva and Milena Lazarova Can machine learning transform internal audit from sampling to full-population surveillance? This study applies supervised classification models to 69,158 billing records from an SAP production environment, comparing SoftMax regression and XGBoost across six risk categories. XGBoost achieves 99% overall accuracy with a macro F1 of 0.965—significantly outperforming logistic regression. The findings show that ML output enables early investigation of suspicious transactions, strengthening internal controls and continuous auditing within enterprise risk management frameworks. 👉 https://brnw.ch/21x5Vvk #FraudDetection #ArtificialIntelligence #RiskManagement #InternalControls

🙌 #Publications2024 #highlycited #DigitalBanking #FinancialInclusion - 9 October ✔️ Digital Risk and Financial Inclusion: Balance between Auxiliary Innovation and Protecting Digital Banking Customers ✍️ by Faraz Ahmed, Arsalan Hussain, Sajjad Nawaz Khan, Arsalan Haneef Malik, Muhammad Asim, Sadique Ahmad and Mohammed El‑Affendi Can digital banking expand financial inclusion without compromising customer protection? This study investigates five key factors influencing customer safety in Pakistan's digital financial services. The findings reveal all factors positively impact protection—with information security carrying the most weight. The results position robust cybersecurity as the critical driver for sustainable growth and competitiveness in digital banking. 👉 https://brnw.ch/21x6huh #CustomerProtection #CyberSecurity #DigitalRisk #RiskManagement #FinTech #BankingInnovation