“We consider an insurance company which faces financial risk in the form of insurance claims and market-dependent surplus fluctuations. The company aims to simultaneously control its terminal wealth (e.g. at the end of an accounting period) and the ruin probability in a finite time interval by purchasing reinsurance… We solve the problem of finding the optimal reinsurance strategy and the corresponding maximal target functional via neural networks.”
Advancements in AI have reshaped risk analysis, emphasizing scalability, explainability, and simplified reporting. This paper urges the risk field to lead in establishing ethical standards and best practices, calling for research to develop guidelines for emerging applications in risk science."
The paper examines non-linearities in how geopolitical risk (GPR) shocks affect the economy. Using a VARX model, it finds that large GPR shocks (above 4 standard deviations) significantly increase uncertainty, leading to precautionary saving and reduced consumption, with a more moderate impact on inflation due to conflicting demand and uncertainty effects.
This study provides semi-explicit formulas for inf-convolution and optimal allocations, considering homogeneous, conditional, and absolutely continuous beliefs. The research also explores inf-convolution between Lambda value at risk and other risk measures, discussing optimal allocations and alternative Lambda value at risk definitions.
“ In this paper, we propose an efficient important sampling method for distortion risk measures in such models that reduces the computational cost through machine learning. We demonstrate the applicability and efficiency of the Monte Carlo method in numerical experiments on various distortion risk measures and models.”An Integrated App”
Climate risk modeling provides quantitative data on potential risks at various scales. However, integrating qualitative data and local knowledge can enhance and validate these assessments.
This study explores a Bayesian approach to Pay-As-You-Drive (PAYD) insurance, using Naive Bayes classifiers and Bayesian Networks for risk assessment. It achieved 87.5% accuracy in predicting risk and improved interpretability over traditional models, optimizing pricing strategies and promoting affordable coverage by dismissing geographic grouping in insurance pricing.
“... commitments to ESG might be viewed as signalling a particular approach to risk management rather than an ideologically-driven willingness to sacrifice profitability.”
The paper examines the EU AI Act's impact on banking supervision, highlighting the ECB's role. It discusses legal frameworks, obligations for high-risk AI systems, AI governance, and the balance between innovation and prudential requirements. Strategic policy recommendations are provided to enhance oversight and financial system integrity.
“... insurers’ asset allocation and product pricing decisions are more connected than previously thought.”