arXiv subjects

Rodrigo S. Targino

Publications and source records attributed to Rodrigo S. Targino.

15 recordsLinked to original sources

arXiv2026

A Reverse-BSDE Diffusion Sampler

Diffusion-based generative models have renewed interest in stochastic differential equation methods for sampling from complex distributions. We study a setting in which the target density is known only up to a normalizing constant and reformulate the reverse-time diffusion sampler as a forward-backward stochastic differential equation (FBSDE). This formulation replaces the separate pre-estimation of the time-dependent score with the solution of a coupled stochastic system. We prove the equivalence of these formulations and provide a decomposition of the approximation error arising from initializing the sampler with a standard Gaussian, applying Euler discretization to the dynamics, and solving the FBSDE approximately. We then evaluate the proposed algorithm on synthetic targets, including separated mixtures, anisotropic Gaussian distributions, and banana-shaped and ring-shaped distributions. The results demonstrate the promise of the method, particularly for targets with complex global structure.

stat.ML↗

arXiv2026

A New Perspective on Reverse Diffusion for Monte Carlo Sampling

This paper introduces a novel perspective on the use of reverse diffusion processes for sampling from unnormalized densities. The central idea is to embed the target density as the marginal at the initial time of a suitably constructed diffusion process evolving over a finite horizon. In contrast to existing approaches, the proposed methodology involves neither time discretization error nor score function estimation, so that Monte Carlo variability is the only source of approximation. A key theoretical result characterizes the Radon-Nikodym derivative of the reverse diffusion transition distribution with respect to that of an Ornstein-Uhlenbeck (OU) process. This representation provides a tractable change-of-measure formulation and serves as the foundation for two distinct classes of Monte Carlo algorithms. The first class approximates the reverse transition distribution via a sequence of pseudo-marginal Metropolis-Hastings MCMC algorithms. The resulting scheme produces an approximate i.i.d. sample from the target distribution and is fully parallelizable, as trajectories can be generated independently. The second class consists of MCMC algorithms targeting the joint law of the whole diffusion path in $[0,T]$, for a suitably chosen horizon $T$. The proposed samplers combine three types of updates. One update simulates the diffusion forward in time according to an OU dynamics, conditional on its initial value. The remaining two update the backward component via Metropolis-type steps: one conditions on the terminal value at time $T$ and the other one does not. In both cases, acceptance probabilities are implemented using Barker-type Bernoulli factory constructions. The proposed methods perform well for targets with multimodality and complex dependence structures, providing a scalable and efficient alternative to the widely used random-walk Metropolis algorithm.

stat.CO↗

arXiv2026

Negative binomial models for development triangles of counts

Prediction of outstanding claims has been done via nonparametric models (chain ladder), semiparametric models (overdispersed poisson) or fully parametric models. In this paper, we propose models based on negative binomial distributions for the prediction of outstanding number of claims, which are particularly useful to account for overdispersion. We first assume independence of random variables and introduce appropriate notation. Later, we generalise the model to account for dependence across development years. In both cases, the marginal distributions are negative binomials. We study the properties of the models and carry out bayesian inference. We illustrate the performance of the models with simulated and real datasets.

stat.ME↗

arXiv2025

Conformal prediction for frequency-severity modeling

We present a model-agnostic framework for the construction of prediction intervals of insurance claims, with finite sample statistical guarantees, extending the technique of split conformal prediction to the domain of two-stage frequency-severity modeling. The framework effectiveness is showcased with simulated and real datasets using classical parametric models and contemporary machine learning methods. When the underlying severity model is a random forest, we extend the two-stage split conformal prediction algorithm, showing how the out-of-bag mechanism can be leveraged to eliminate the need for a calibration set in the conformal procedure.

stat.ME↗

arXiv2025

Analyzing Pension Fund Mortality with Gaussian Processes in a Sub Population Framework

Pension fund populations often have mortality experiences that are substantially different from the national benchmark. In a motivating case study of Brazilian corporate pension funds, pensioners are observed to have mortality that is 40-55% below the national average, due to the underlying socioeconomic disparities. Direct analysis of a pension fund population is challenging due to very sparse data, with age-specific annual death counts often in low single digits. We design and study a collection of stochastic sub-population frameworks that coherently capture and project pensioner mortality rates via deflator factors relative to a reference population. Superseding parametric approaches, we propose Gaussian process (GP) based models that flexibly estimate Age- and/or Year-specific deflators. We demonstrate that the GP models achieve better goodness of fit and uncertainty quantification. Our models are illustrated on two Brazilian pension funds in the context of exogenous national and insurance industry mortality tables. The GP models are implemented in R Stan using a fully Bayesian approach and take into account over-dispersion relative to the Poisson likelihood.

stat.AP↗

arXiv2025

Mensuração da Transferência de Riqueza em Planos de Contribuição Definida com a Marcação de Ativos na Curva

The methodology for measuring financial assets in defined contribution (DC) pension plans has significant implications whether wealth transfers will occur among participants. In December 2024, a regulatory act was issued for Closed Pension Entities, allowing the use of the hold-to-maturity (HTM) measurement method of treasury bonds in DC plans. This article quantifies the financial impact on participants of adopting HTM valuation in these plans, using real data from the term structure of the real interest rates to assess the resulting wealth transfers. The analysis highlights how HTM valuation creates asymmetries in financial outcomes, benefiting some participants at the expense of others. Wealth transfers occur both during any withdrawal of funds and at the time of contributions, including portfolio reallocations that involve buying or selling bonds. Partial use of HTM or attempts to immunize outflows do not completely eliminate wealth transfers. The results reinforce that the use of mark-to-market (MTM) valuation of assets in DC plans prevents wealth transfers and, consequently, financial losses for participants. O método de mensuração de ativos financeiros em planos de previdência na modalidade de contribuição definida (CD, ou contribuição variável CV, na fase de acumulação) tem implicações significativas se haverá transferência de riqueza entre os participantes. Em Dez/2024 foi publicada norma para as Entidades Fechadas de Previdência Complementar possibilitando o uso da marcação na curva de títulos públicos federais nos planos CD e CV na fase de acumulação. Este artigo quantifica o impacto financeiro nos participantes da adoção da marcação na curva (HTM {\it Hold to Maturity}) nestes planos, utilizando dados reais da estrutura a termo da taxa de juros de cupom de IPCA para avaliar as transferências de riqueza resultantes dessa adoção. A análise evidencia como a marcação na curva gera assimetrias nos resultados financeiros, beneficiando alguns participantes em detrimento de outros. As transferências de riqueza ocorrem tanto em qualquer retirada de recursos quanto também na entrada (contribuições), inclusive realocações da carteira que impliquem venda ou compra de títulos. O uso do HTM de forma parcial ou a tentativa de imunização de saídas não eliminam por completo transferências de riqueza. Os resultados reforçam que, para fins de cotização, o uso da marcação a mercado (MTM {\it Mark to Market}) de ativos em planos CD (e CV na fase de diferimento) evita transferências de riqueza e, por consequência, prejuízos financeiros aos seus participantes.

econ.GN↗

arXiv2024

Risk Budgeting Allocation for Dynamic Risk Measures

We define and develop an approach for risk budgeting allocation - a risk diversification portfolio strategy - where risk is measured using a dynamic time-consistent risk measure. For this, we introduce a notion of dynamic risk contributions that generalise the classical Euler contributions and which allow us to obtain dynamic risk contributions in a recursive manner. We prove that, for the class of coherent dynamic distortion risk measures, the risk allocation problem may be recast as a sequence of strictly convex optimisation problems. Moreover, we show that self-financing dynamic risk budgeting strategies with initial wealth of 1 are scaled versions of the solution of the sequence of convex optimisation problems. Furthermore, we develop an actor-critic approach, leveraging the elicitability of dynamic risk measures, to solve for risk budgeting strategies using deep learning.

q-fin.MF↗

arXiv2023

Stochastic modelling of football matches

This paper develops a general framework for stochastic modeling of goals and other events in football (soccer) matches. The events are modelled as Cox processes (doubly stochastic Poisson processes) where the event intensities may depend on all the modeled events as well as external factors. The model has a strictly concave log-likelihood function which facilitates its fitting to observed data. Besides event times, the model describes the random lengths of stoppage times which can have a strong influence on the final score of a match. The model is illustrated on eight years of data from Campeonato Brasileiro de Futebol Série A. We find that dynamic regressors significantly improve the in-game predictive power of the model. In particular, a) when a team receives a red card, its goal intensity decreases more than 30%; b) the goal rate of a team increases by 10% if it is losing by one goal and by 20% if its losing by two goals; and c) when the goal difference at the end of the second half is less than or equal to one, the stoppage time is on average more than one minute longer than in matches with a difference of two goals.

stat.AP↗

arXiv2023

Risk Budgeting Portfolios from Simulations

Risk budgeting is a portfolio strategy where each asset contributes a prespecified amount to the aggregate risk of the portfolio. In this work, we propose an efficient numerical framework that uses only simulations of returns for estimating risk budgeting portfolios. Besides a general cutting planes algorithm for determining the weights of risk budgeting portfolios for arbitrary coherent distortion risk measures, we provide a specialised version for the Expected Shortfall, and a tailored Stochastic Gradient Descent (SGD) algorithm, also for the Expected Shortfall. We compare our algorithm to standard convex optimisation solvers and illustrate different risk budgeting portfolios, constructed using an especially designed Julia package, on real financial data and compare it to classical portfolio strategies.

q-fin.PM↗

arXiv2022

Avoiding zero probability events when computing Value at Risk contributions

This paper is concerned with the process of risk allocation for a generic multivariate model when the risk measure is chosen as the Value-at-Risk (VaR). We recast the traditional Euler contributions from an expectation conditional on an event of zero probability to a ratio involving conditional expectations whose conditioning events have strictly positive probability. We derive an analytical form of the proposed representation of VaR contributions for various parametric models. Our numerical experiments show that the estimator using this novel representation outperforms the standard Monte Carlo estimator in terms of bias and variance. Moreover, unlike the existing estimators, the proposed estimator is free from hyperparameters under a parametric setting.

q-fin.CP↗

arXiv2019

Modelling dependence within and across run-off triangles for claims reserving

We propose a stochastic model for claims reserving that captures dependence along development years within a single triangle. This dependence is of autoregressive form of order $p$ and is achieved through the use of latent variables. We carry out bayesian inference on model parameters and borrow strength across several triangles, coming from different lines of businesses or companies, through the use of hierarchical priors.

stat.AP↗

arXiv2018

Bayesian Approach for Parameter Estimation of Continuous-Time Stochastic Volatility Models using Fourier Transform Methods

We propose a two stage procedure for the estimation of the parameters of a fairly general, continuous-time stochastic volatility. An important ingredient of the proposed method is the Cuchiero-Teichmann volatility estimator, which is based on Fourier transforms and provides a continuous time estimate of the latent process. This estimate is then used to construct an approximate likelihood for the parameters of interest, whose restrictions are taken into account through prior distributions. The procedure is shown to be highly successful for constructing the posterior distribution of the parameters of a Heston model, while limited success is achieved when applied to the highly parametrized exponential-Ornstein-Uhlenbeck.

math.ST↗

arXiv2015

Sequential Monte Carlo Samplers for capital allocation under copula-dependent risk models

In this paper we assume a multivariate risk model has been developed for a portfolio and its capital derived as a homogeneous risk measure. The Euler (or gradient) principle, then, states that the capital to be allocated to each component of the portfolio has to be calculated as an expectation conditional to a rare event, which can be challenging to evaluate in practice. We exploit the copula-dependence within the portfolio risks to design a Sequential Monte Carlo Samplers based estimate to the marginal conditional expectations involved in the problem, showing its efficiency through a series of computational examples.

stat.CO↗

arXiv2013

Optimal insurance purchase strategies via optimal multiple stopping times

In this paper we study a class of insurance products where the policy holder has the option to insure $k$ of its annual Operational Risk losses in a horizon of $T$ years. This involves a choice of $k$ out of $T$ years in which to apply the insurance policy coverage by making claims against losses in the given year. The insurance product structure presented can accommodate any kind of annual mitigation, but we present three basic generic insurance policy structures that can be combined to create more complex types of coverage. Following the Loss Distributional Approach (LDA) with Poisson distributed annual loss frequencies and Inverse-Gaussian loss severities we are able to characterize in closed form analytical expressions for the multiple optimal decision strategy that minimizes the expected Operational Risk loss over the next $T$ years. For the cases where the combination of insurance policies and LDA model does not lead to closed form expressions for the multiple optimal decision rules, we also develop a principled class of closed form approximations to the optimal decision rule. These approximations are developed based on a class of orthogonal Askey polynomial series basis expansion representations of the annual loss compound process distribution and functions of this annual loss.

q-fin.RM↗

arXiv2013

Understanding Operational Risk Capital Approximations: First and Second Orders

We set the context for capital approximation within the framework of the Basel II / III regulatory capital accords. This is particularly topical as the Basel III accord is shortly due to take effect. In this regard, we provide a summary of the role of capital adequacy in the new accord, highlighting along the way the significant loss events that have been attributed to the Operational Risk class that was introduced in the Basel II and III accords. Then we provide a semi-tutorial discussion on the modelling aspects of capital estimation under a Loss Distributional Approach (LDA). Our emphasis is to focus on the important loss processes with regard to those that contribute most to capital, the so called high consequence, low frequency loss processes. This leads us to provide a tutorial overview of heavy tailed loss process modelling in OpRisk under Basel III, with discussion on the implications of such tail assumptions for the severity model in an LDA structure. This provides practitioners with a clear understanding of the features that they may wish to consider when developing OpRisk severity models in practice. From this discussion on heavy tailed severity models, we then develop an understanding of the impact such models have on the right tail asymptotics of the compound loss process and we provide detailed presentation of what are known as first and second order tail approximations for the resulting heavy tailed loss process. From this we develop a tutorial on three key families of risk measures and their equivalent second order asymptotic approximations: Value-at-Risk (Basel III industry standard); Expected Shortfall (ES) and the Spectral Risk Measure. These then form the capital approximations.

q-fin.RM↗