A Novel Scaling Approach for Unbiased Adjustment of Risk Estimators

The paper introduces a new approach to risk scaling, addressing challenges like limited data and heavy tails in risk assessment. It offers a robust, conservative method for estimating capital reserves, going beyond traditional scaling laws. The proposed framework improves long-term risk estimation, risk transfers, and backtesting performance, with empirical validation.

Can the AML system be evaluated without better data?

The Anti-Money Laundering (AML) regime has harmonized laws globally but lacks credible data on its effectiveness. Evaluations are inconsistent and infrequent, relying on outdated data. Without systematic analysis, claims of effectiveness may be considered subjective, undermining legitimacy despite potential impacts of AML efforts.

Reinsurance with neural networks

“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.”

Geopolitical Risk Shocks: When the Size Matters

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.

Risk sharing with Lambda value at risk under heterogeneous beliefs

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.

An Integrated Approach to Importance Sampling and Machine Learning for Efficient Monte Carlo Estimation of Distortion Risk Measures in Black Box Models

“ 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”