Welcome to the Finance-Insurance Group. We are a group of driven researchers specialized in the quantitative analysis of finance and insurance problems. The group has accompanied the growth of CREST since its creation, and is now composed of 7 permanent researchers, 2 emeritus professors and 10 PhD students, plus several affiliates from Parisian Universities and Business Schools.

We publish in the top international journals in our field (Econometrica, Management Science, Journal of Econometrics, Mathematical Finance, Finance & Stochastics, J. of Financial Econometrics, Insurance: Mathematics & Economics, etc), regularly participate in major international conferences and organize specialized conferences and seminars.

Our research encompasses a wide spectrum of fields in finance and actuarial science : financial econometrics, mathematical finance, risk management, green finance, etc. Historical topics of the Group include among others: i) the study of GARCH-type models, ii) Portfolio optimization, iii) the Econometrics of conditional risks, iv) Regulation, systemic risks and contagion, v) Dependence modeling and copulas.

We also aim at developing new areas of research, like those related to emerging risks (cyber-risks, environmental risks, longevity risks), new markets (in particular, in the energy sector), new models (e.g., for  environmental economics), new types of data (e.g., high-frequency data and integer-valued financial time series), or new statistical approaches (e.g., machine learning techniques, or the use of noncausal models for bubble prediction).

Additionally, we aim at creating a stimulating learning and research environment for students in Finance and Actuarial Science, in particular at the Master and PhD levels. Beyond the academic research, we are also motivated by applications to real problems and have developed links with the finance and insurance industry, in particular through research Chaires.

Contacts

Jean-David Fermanian (Director)

Fanda Traoré (Administrative Coordinator)

finance

Bayesian credibility model with heavy tail random variables: calibration of the prior and application to natural disasters and cyber insurance

The Bayesian credibility approach is a method for evaluating a certain risk of a segment of a portfolio (such as policyholder or category of policyholders) by compensating for the lack of historical d ...

Heranval Antoine, Lopez Olivier & Thomas Maud

European Actuarial Journal, 2024

finance

Semiparametric copula models applied to the decomposition of claim amounts

In this paper, we develop a conditional copula model to analyze the distribution of a claim that generates different types of costs and/or simultaneously impacts several guarantees. Our methodology is ...

Farkas Sebastien, Lopez Olivier

Scandinavian Actuarial Journal, 2024

finance

Generalized pareto regression trees for extreme event analysis

This paper derives finite sample results to assess the consistency of Generalized Pareto regression trees introduced by Farkas et al. (Insur. Math. Econ. 98:92--105, 2021) as tools to perform extreme ...

Farkas Sebastien, Heranval Antoine, Lopez Olivier, Thomas, Maud

Extremes, 2024