Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Valérie Chavez-Demoulin is active.

Publication


Featured researches published by Valérie Chavez-Demoulin.


Journal of Operational Risk | 2006

Infinite-mean models and the LDA for operational risk

Johanna Nešlehová; Paul Embrechts; Valérie Chavez-Demoulin

Due to published statistical analyses of operational risk data, methodological approaches to the AMA modeling of operational risk can be discussed more in detail. In this paper we raise some issues concerning correlation (or diversification) effects, the use of extreme value theory and the overall quantitative risk management consequences of extremely heavy-tailed data. We especially highlight issues around infinite mean models. Besides methodological examples and simulation studies, the paper contains indications for further research.


Quantitative Finance | 2005

Estimating value-at-risk: a point process approach

Valérie Chavez-Demoulin; A. C. Davison; Alexander J. McNeil

We consider the modelling of extreme returns in financial time series, and introduce a marked point process model for the exceedances of a high threshold. This model has a self-exciting, Hawkes-process structure in which recent events affect the current intensity of threshold exceedances more than distant ones. Estimates of value-at-risk are derived for real datasets and the success of the estimation method is evaluated in backtests.


Journal of Risk and Insurance | 2016

An Extreme Value Approach for Modeling Operational Risk Losses Depending on Covariates

Valérie Chavez-Demoulin; Paul Embrechts; Marius Hofert

A general methodology for modeling loss data depending on covariates is developed. The parameters of the frequency and severity distributions of the losses may depend on covariates. The loss frequency over time is modeled with a nonhomogeneous Poisson process with rate function depending on the covariates. This corresponds to a generalized additive model, which can be estimated with spline smoothing via penalized maximum likelihood estimation. The loss severity over time is modeled with a nonstationary generalized Pareto distribution (alternatively, a generalized extreme value distribution) depending on the covariates. Since spline smoothing cannot directly be applied in this case, an efficient algorithm based on orthogonal parameters is suggested. The methodology is applied both to simulated loss data and a database of operational risk losses collected from public media. Estimates, including confidence intervals, for risk measures such as Value‐at‐Risk as required by the Basel II/III framework are computed. Furthermore, an implementation of the statistical methodology in R is provided.


Journal of Econometrics | 2014

Extreme-Quantile Tracking for Financial Time Series

Valérie Chavez-Demoulin; Paul Embrechts; Sylvain Sardy

Time series of financial asset values exhibit well known statistical features such as heavy tails and volatility clustering. Strongly present in some series, nonstationarity is a feature that has been somewhat overlooked. This may however be a highly relevant feature when estimating extreme quantiles (VaR) for such series. We propose a nonparametric extension of the classical Peaks-Over-Threshold method to fit the time varying volatility in situations where the stationarity assumption is strongly violated by erratic changes of regime. A back testing study for the UBS share price over the subprime crisis reveals that our approach provides better extreme-quantile (VaR) estimates than methods that ignore nonstationarity.


Journal of Multivariate Analysis | 2015

Generalized additive models for conditional dependence structures

Thibault Vatter; Valérie Chavez-Demoulin

We develop a generalized additive modeling framework for taking into account the effect of predictors on the dependence structure between two variables. We consider dependence or concordance measures that are solely functions of the copula, because they contain no marginal information: rank correlation coefficients or tail-dependence coefficients represent natural choices. We propose a maximum penalized log-likelihood estimator, derive its n -consistency and asymptotic normality, discuss details of the estimation procedure and the selection of the smoothing parameter. Finally, we present the results from a simulation study and apply the new methodology to a real dataset. Using intraday asset returns, we show that an intraday dependence pattern, due to the cyclical nature of market activity, is shaped similarly to the individual conditional second moments.


Communications in Statistics-theory and Methods | 2010

Revisiting the Edge, Ten Years On

Valérie Chavez-Demoulin; Paul Embrechts

When these lines are written, it is January 21, 2008, a further “Black Monday” on the international markets. Stock indices have fallen between 5 and 10%. Which statistical tools help in describing such events and may help in understanding the consequences? In this article we update our knowledge on the modeling of extremal events, in particular with a view toward applications to finance, insurance, and risk management.


Production Planning & Control | 2014

Do flow principles of operations management apply to computing centres

Felipe Abaunza; Valérie Chavez-Demoulin; Ari-Pekka Hameri; Tapio Niemi

By analysing large data-sets on jobs processed in major computing centres, we study how operations management principles apply to these modern day processing plants. We show that Little’s Law on long-term performance averages holds to computing centres, i.e. work-in-progress equals throughput rate multiplied by process lead time. Contrary to traditional manufacturing principles, the law of variation does not hold to computing centres, as the more variation in job lead times the better the throughput and utilisation of the system. We also show that as the utilisation of the system increases lead times and work-in-progress increase, which complies with traditional manufacturing. In comparison with current computing centre operations these results imply that better allocation of jobs could increase throughput and utilisation, while less computing resources are needed, thus increasing the overall efficiency of the centre. From a theoretical point of view, in a system with close to zero set-up times, as in the case of computing centres, the law of variation does not hold. We observe that the more variation in job lead times and resource usage, the higher the throughput of the system.


International Journal of Operations & Production Management | 2013

Turnaround across diverse global supply chains using shared metrics and change methodology: The case of Amer Sports Corporation

Valérie Chavez-Demoulin; Ari-Pekka Hameri; Jussi Heikkilä; Vincent Wauters

Purpose – The purpose of this paper is to document the outcome of a global three‐year long supply chain improvement initiative at a multi‐national producer of branded sporting goods that is transforming from a holding structure to an integrated company. The case company is comprised of seven internationally well‐known sport brands, which form a diverse set of independent sub‐cases, on which the same supply chain metrics and change project approach was applied to improve supply chain performance.Design/methodology/approach – By using in‐depth case study and statistical analysis the paper analyzes across the brands how supply chain complexity (SKU count), supply chain type (make or buy) and seasonality affect completeness and punctuality of deliveries, and inventory as the change project progresses.Findings – Results show that reduction in supply chain complexity improves delivery performance, but has no impact on inventory. Supply chain type has no impact on service level, but brands with in‐house producti...


International Journal of Retail & Distribution Management | 2016

Weather and supply chain performance in sport goods distribution

Flora Babongo; Valérie Chavez-Demoulin; Ari-Pekka Hameri; Tapio Niemi

Purpose – The purpose of this paper is to study how variations in weather affect demand and supply chain performance in sport goods. The study includes several brands differing in supply chain structure, product variety and seasonality. Design/methodology/approach – Longitudinal data on supply chain transactions and customer weather conditions are analysed. The underlying hypothesis is that changes in weather affect demand, which in turn impacts supply chain performance. Findings – In general, an increase in temperature in winter and spring decreases order volumes in resorts, while for larger customers in urban locations order volumes increase. Further, an increase in volumes of non-seasonal products reduces delays in deliveries, but for seasonal products the effect is opposite. In all, weather affects demand, lower volumes do not generally improve supply chain performance, but larger volumes can make it worse. The analysis shows that the dependence structure between demand and delay is time varying and i...


Journal of Multivariate Analysis | 2017

Non-Linear Models for Extremal Dependence

Linda Mhalla; Valérie Chavez-Demoulin; Philippe Naveau

The dependence structure of max-stable random vectors can be characterized by their Pickands dependence function. In many applications, the extremal dependence measure varies with covariates. We develop a flexible, semi-parametric method for the estimation of non-stationary multivariate Pickands dependence functions. The proposed construction is based on an accurate max-projection allowing to pass from the multivariate to the univariate setting and to rely on the generalized additive modeling framework. In the bivariate case, the resulting estimator of the Pickands function is regularized using constrained median smoothing B-splines, and bootstrap variability bands are constructed. In higher dimensions, we tailor our approach to the estimation of the extremal coefficient. An extended simulation study suggests that our estimator performs well and is competitive with the standard estimators in the absence of covariates. We apply the new methodology to a temperature dataset in the US where the extremal dependence is linked to time and altitude.

Collaboration


Dive into the Valérie Chavez-Demoulin's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar

A. C. Davison

École Polytechnique Fédérale de Lausanne

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Tapio Niemi

Helsinki Institute of Physics

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Kshitij Sharma

École Polytechnique Fédérale de Lausanne

View shared research outputs
Top Co-Authors

Avatar

Pierre Dillenbourg

École Polytechnique Fédérale de Lausanne

View shared research outputs
Researchain Logo
Decentralizing Knowledge