We develop a statistical framework to benchmark and select large language models based on their risks.
problem Benchmarking and selecting large language models based on their associated risks.
method A distributional framework using first and second order stochastic dominance, linked to mean-risk models in finance.
result Formalizes a risk-aware approach for model selection, balancing risk and utility.
Risk statistic is a critical factor not only for risk analysis but also for financial application. However, the traditional risk statistics may fail to describe the characteristics of regulator-based risk. In this paper, we consider the regulator-based risk statistics for portfolios. By further developing the propertie…
New statistical factors improve portfolio risk estimation.
problem Improving estimation of portfolio risk using new statistical factors.
method Matrix factor models and statistical methods (partial F test, double selection LASSO).
result New statistical factors add explanatory power in asset pricing.
L-ARC improves model fairness by localizing risk guarantees.
problem Improving model fairness in tasks like image segmentation and wireless networks.
method Localized Adaptive Risk Control (L-ARC) updates a threshold function in RKHS to target localized statistical risk guarantees.
result L-ARC produces prediction sets with improved fairness across different data subpopulations.
Paper tackles complex risk in deep neural networks.
problem Complex risk in deep neural networks.
method Developed new approach for complex risk statistics.
result Derived dual representation for complex risk.
As regulators pay more attentions to losses rather than gains, we are able to derive a new class of risk statistics, named regulator-based risk statistics with scenario analysis in this paper. This new class of risk statistics can be considered as a kind of risk extension of risk statistics introduced by Kou et al. \ci…
The time value of money is a critical factor not only in risk analysis, but also in insurance and financial applications. In this paper, we consider a special class of set-valued risk statistics by introducing the time value of money. In fact, the risk statistics established by this method is closer to financial realit…
Develops a statistical framework for coherent risk estimation.
problem Constructing coherent risk estimators with sound financial and statistical properties.
method Inspired by axiomatic risk measure theory, defines coherent risk estimators through robust representations linked to L-estimators. result Demonstrates that coherence of a risk measure does not necessarily carry over to its estimators and shows alternative weight structures can lead to different outcomes.
Research evaluates three risk models for portfolio construction during market downturns.
problem Challenges in constructing quantitative portfolios using statistical risk models.
method Three statistical risk models tested on 1,000 stocks across four periods.
result Models consistently outperform market returns in various crises.
A new method for backtesting ES forecasts in banking.
problem Designing a model-free backtesting procedure for Expected Shortfall forecasts.
method Use e-values and e-processes to introduce backtest e-statistics for VaR and ES.
result The proposed method can be applied to various risk measures and statistical quantities.
The paper analyzes the risk of investing in a basket of 27 cryptocurrencies using statistical distributions.
problem Risk assessment of capital allocation in a basket of cryptocurrencies.
method Used statistical tests to determine the most appropriate distribution (SDI) for modeling returns, and adapted the generalized Pareto distribution for tail risk assessment.
result Found that a combination of stable and generalized Pareto distributions provides a more accurate risk assessment for the basket of cryptocurrencies.
This research proposes methods to model and assess liability liquidity risk in asset management.
problem Lack of standardized models for liability liquidity risk in asset management.
method Statistical models, zero-inflated models, aggregate and individual-based approaches, and factor models.
result Developed mathematical and statistical approaches to estimate and assess redemption shocks.
New framework calibrates models to control risk under performativity.
problem Calibrating models to ensure reliable decision-making under performativity.
method Iteratively refined calibration process for different risk measures and tail bounds.
result Statistically rigorous risk control under performativity demonstrated.
Score attack method provides a lower bound on privacy-constrained minimax risk.
problem Characterizing the optimality of privacy-constrained statistical models.
method Score attack based on tracing attack concept.
result Optimally lower bounds the minimax risk of estimating unknown model parameters.
We give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The resultant covariance matrices are not factor models. Based on empirical backtests, we compare the performance of these machine learning risk models to other constructions, including statistical risk mode…
Study tests if equity factors explain Bitcoin's risk and returns.
problem Explaining Bitcoin's risk and return with equity factors.
method Applied statistical methods to test Fama-French factors on Bitcoin's excess returns.
result Fama-French factors have explanatory power on Bitcoin's risk and returns.
Investigates JM for reducing downside risk in market regimes.
problem Mitigating downside risk during market downturns.
method Statistical jump model for identifying market regimes, optimizing penalty for state transitions.
result JM-guided strategies outperform traditional models in reducing risk and enhancing returns.
Develops a statistical model for SOFR term structure in incomplete markets.
problem Incomplete liquidity and completeness in SOFR derivatives market.
method Statistical model incorporating macroeconomic factors and jumps in SOFR rates.
result Model is well-suited for risk management and derivatives pricing.
Study tests if deep hedging differs from delta hedging in a GARCH market model.
problem Whether deep hedging includes speculative components in a GARCH market.
method Tested in a GARCH-based market model, comparing deep hedging and delta hedging.
result The difference between deep hedging and delta hedging is speculative if risk measure does not prioritize adverse outcomes.
DeRisk improves credit risk prediction using deep learning.
problem Challenges in training deep neural networks with real-world financial data.
method DeRisk, an effective deep learning framework for credit risk prediction.
result DeRisk outperforms statistical learning methods in credit risk prediction.
Study on forecasting methods and their causal implications.
problem Understanding the difference between statistical and causal risks in forecasting models.
method Introduce causal learning theory for forecasting, obtain uniform convergence bounds for VAR models.
result First theoretical guarantees for causal generalization in time-series forecasting.
Improves statistical learning bounds with self-concordant losses.
problem Statistical prediction with nuisance components.
method Orthogonal statistical learning with self-concordant loss.
result Non-asymptotic bounds on excess risk improved by a dimension factor.
Model assesses credit risk using behavioral data from Experian and Bank of Italy.
problem Improving credit risk assessment in financial institutions.
method Statistical and machine learning techniques applied to behavioral data from Experian and Bank of Italy.
result Demonstrates transferability of the model from private to central data.
This research improves value-at-risk estimation during financial crises using non-extensive statistical methods.
problem Underestimation of value-at-risk during financial crises.
method Non-extensive value-at-risk model based on Tsallis entropy and q-Gaussian probability density function.
result The q-Gaussian model provides better value-at-risk estimation during financial crises.
Framework ensures alignment between humans and machines in LLMs.
problem Human-machine misalignment in LLMs scoring mechanisms.
method Lightweight calibration framework for blackbox models.
result Provably guarantees alignment between humans and machines.
Study excess risk in statistical inference with transformations.
problem Excess risk in estimating random variables from feature vectors and transformations.
method Characterize lossless transformations, develop test statistics, and information-theoretic bounds.
result Strongly consistent partitioning test statistic for lossless transformations.
Enhances risk model with new statistical factors.
problem Missing information in existing risk models.
method Maximum likelihood estimation to refine and add new factors.
result Captures structure missed by original model.
Paper compares neural networks and classical statistics for dementia prediction, highlighting interpretability of classical methods.
problem Tackles the challenge of interpreting risk factors for dementia prediction.
method Compares neural networks and classical statistics for dementia prediction.
result Classical statistics provide clearer interpretation of risk factors compared to neural networks.
Proposes a framework to explain KS deterioration in credit risk models.
problem Inconsistent and ad hoc diagnosis of KS decline in credit risk models.
method Counterfactual diagnostic framework attributing KS decline to sampling variability, portfolio composition, covariate shift, and residual deterioration.
result The proposed approach provides more interpretable and governance-relevant explanations than threshold-based review alone.
The Capital Asset Pricing Model (CAPM) is one of the original models in explaining risk-return relationship in the financial market. However, when applying the CAPM into reality, it demonstrates a lot of shortcomings. While improving the performance of the model, many studies, on one hand, have attempted to apply diffe…
Develops methods for estimating constrained function-valued parameters in infinite-dimensional models.
problem Estimating function-valued parameters with structural constraints in complex models.
method Characterizes constrained solutions as minimizers of penalized population risk, using a Lagrange-type formulation and path through unconstrained space.
result Proposes estimators that achieve optimal risk and constraint satisfaction, applicable across various statistical learning approaches.
Paper discusses extending Gini score for tied rankings and case weights.
problem Extending Gini score for tied rankings and case weights.
method Discuss and adapt Gini score for ties and case weights.
result Gini score can be used for tied rankings and case weights.
We give complete algorithms and source code for constructing statistical risk models, including methods for fixing the number of risk factors. One such method is based on eRank (effective rank) and yields results similar to (and further validates) the method set forth in an earlier paper by one of us. We also give a co…
This paper proposes a new integrated variance estimator based on order statistics within the framework of jump-diffusion models. Its ability to disentangle the integrated variance from the total process quadratic variation is confirmed by both simulated and empirical tests. For practical purposes, we introduce an itera…
The book chapter discusses tail risk analysis for financial data using extreme value statistics.
problem Serial dependence in financial time series complicates tail risk assessment.
method The approach involves unconditional and conditional quantile forecasting.
result Serial dependence impacts multivariate tail dependence.
The study calculates the risk of semi-supervised multitask learning on Gaussian mixtures.
problem Understanding the risk in semi-supervised multitask learning on Gaussian mixtures.
method Statistical physics methods applied to Gaussian mixture models.
result The study evaluates the performance gain of learning tasks together versus separately.
Prove non-asymptotic bounds for minimal risk in statistical learning
problem Estimating minimal risk in statistical learning
method Using concentration inequalities
result Non-asymptotic bounds for minimal risk
The paper examines expectile quadrangle properties in risk management.
problem Exploring the properties of expectile quadrangles in risk management.
method Rigorously examines the properties of expectile quadrangles.
result Rigorously examines the properties of expectile quadrangles.
Paper improves clustering risk bounds for kernel k-means.
problem Improving clustering risk bounds for kernel k-means.
method Analyzes kernel k-means and Nyström approximation.
result Achieves nearly optimal excess clustering risk bound.
This paper investigates how to measure common market risk factors using newly proposed Panel Quantile Regression Model for Returns. By exploring the fact that volatility crosses all quantiles of the return distribution and using penalized fixed effects estimator we are able to control for otherwise unobserved heterogen…
Deep Hedging learns risk-neutral vol dynamics for option pricing.
problem Statistical arbitrage in market dynamics without transaction costs.
method Numerical approach to train market simulator and find risk-neutral density.
result Risk-neutral model for stochastic implied volatility can be used for pricing or Deep Hedging.
Assessment of risk levels for existing credit accounts is important to the implementation of bank policies and offering financial products. This paper uses cluster analysis of behaviour of credit card accounts to help assess credit risk level. Account behaviour is modelled parametrically and we then implement the behav…
Starting from the requirement that risk measures of financial portfolios should be based on their losses, not their gains, we define the notion of loss-based risk measure and study the properties of this class of risk measures. We characterize loss-based risk measures by a representation theorem and give examples of su…
The paper analyzes statistical arbitrage using a factor model of equity returns.
problem Analyzing and trading statistical arbitrage strategies in equity markets.
method Conditional factor model, state space framework, online risk premia estimation, mean reversion trades.
result The model outperforms other methods in statistical arbitrage trading strategies over a 29-year period.
In this study, we analyze the aerospace stocks prices in order to characterize the sector behavior. The data analyzed cover the period from January 1987 to April 1999. We present a new index for the aerospace sector and we investigate the statistical characteristics of this index. Our results show that this index is we…
New algorithms avoid non-monotonic risk curves in statistical learning.
problem Non-monotonic behavior of risk curves in statistical learning.
method Derive risk-monotonic algorithms under weak assumptions.
result Risk monotonicity does not necessarily lead to worse excess risk rates.
This paper derives -- considering a Gaussian setting -- closed form solutions of the statistics that Adrian and Brunnermeier and Acharya et al. have suggested as measures of systemic risk to be attached to individual banks. The statistics equal the product of statistic specific Beta-coefficients with the mean corrected…
The purpose of this research article is to discover how the econophysics analysis can complement the econometrics models in application to the risk management in the central banks and financial institutions, operating within the nonlinear dynamical financial system. We consider the modern risk management models and sho…