Marie Michaelides, PhD.

Doctorat en mathématiques,
UQAM

2024/05

Direction de recherche:

  • Mathieu Pigeon, professeur au Département de mathématiques de l’Université du Québec à Montréal
  • Hélène Cossette, professeure à l’École d’actuariat de l’Université Laval

Thèse de doctorat:

Michaelides, Marie (2024), « Analyse de la dépendance intra-trajectoire dans la modélisation individuelle des réserves en assurance non-vie », Dir.: Mathieu Pigeon et Hélène Cossette, Thèse de doctorat. Montréal (Québec, Canada), Université du Québec à Montréal, Doctorat en mathématiques.

Publications

  • M.Michaelides, H.Cossette & M.Pigeon (2025), Parametric Estimation of Conditional Archimedean Copula Generators for Censored Data, Computational Statistics & Data Analysis, p. 108309.

    In this paper, we propose a novel approach for estimating Archimedean copula generators in a conditional setting, incorporating endogenous variables. Our method allows for the evaluation of the impact of the different levels of covariates on both the strength and shape of dependence by directly estimating the generator function rather than the copula itself. As such, we contribute to relaxing the simplifying assumption inherent in traditional copula modeling. We demonstrate the effectiveness of our methodology through applications in two diverse settings: a diabetic retinopathy study and a claims reserving analysis. In both cases, we show how considering the influence of covariates enables a more accurate capture of the underlying dependence structure in the data, thus enhancing the applicability of copula models, particularly in actuarial contexts.

  • M.Michaelides, H.Cossette & M.Pigeon (2025), Simulations of Archimedean copulas from their non- parametric generators for loss reserving under flexible censoring, North American Actuarial Journal, 1-28

    In this paper, we propose a novel approach for estimating Archimedean copula generators in a conditional setting, incorporating endogenous variables. Our method allows for the evaluation of the impact of the different levels of covariates on both the strength and shape of dependence by directly estimating the generator function rather than the copula itself. As such, we contribute to relaxing the simplifying assumption inherent in traditional copula modeling. We demonstrate the effectiveness of our methodology through applications in two diverse settings: a diabetic retinopathy study and a claims reserving analysis. In both cases, we show how considering the influence of covariates enables a more accurate capture of the underlying dependence structure in the data, thus enhancing the applicability of copula models, particularly in actuarial contexts.

  • M.Michaelides, H.Cossette & M.Pigeon (2023), Individual Claims Reserving Using Activation Patterns, European Actuarial Journal, 13(2), 837-869.

    The occurrence of a claim often impacts not one but multiple insurance coverages provided in the contract. To account for this multivariate feature, we propose a new individual claims reserving model built around the activation of the different coverages to predict the reserve amounts. Using the framework of multinomial logistic regression, we model the activation of the different insurance coverages for each claim and their development in the following years, i.e. the activation of other coverages in the later years and all the possible payments that might result from them. As such, the model allows us to complete the individual development of the open claims in the portfolio. Using a recent automobile dataset from a major Canadian insurance company, we demonstrate that this approach generates accurate predictions of the total reserves as well as of the reserves per insurance coverage. This allows the insurer to get better insights in the dynamics of his claims reserves.

Présentations scientifiques

  • A Non-Parametric Estimator for Archimedean Copulas under Flexible Censoring Scenarios and an Application to Claims Reserving, Séminaire Quantact en mathématiques actuarielles et financières, Université Laval, Québec, Canada (QC), 9 février 2024.
  • Individual Claims Reserving With Dependent Censored Data, International Congress on Insurance: Mathematics and Economics, Édimbourg, Royaume-Uni, 4 juillet 2023.
  • Individual Claims Reserving With Dependent Censored Data, Insurance Data Science Conference, Londres, Royaume-Uni, 15 juin 2023.
  • Individual Claims Reserving Using Activation Patterns, 15th International Conference of the ERCIM WG on Computation and Methodological Statistics (CMStatistics 2022), Londres, Royaume-Uni, 17 décembre 2022.
  • Individual Claims Reserving Using Activation Patterns, 3rd Waterloo Student Conference in Statistics, University of Waterloo, Canada (ON), 14 octobre 2022.
  • Individual Claims Reserving Using Activation Patterns, Actuarial Research Conference (ARC), University of Illinois, Urbana-Champaign, USA (IL), 3 août 2022.
  • Individual Claims Reserving Using Activation Patterns, Quantact SummerDay, Université Concordia, Montréal, Canada (QC), 22 juillet 2022.

Implications

Présentations locales

  • Individual Claims Reserving With Dependent Censored Data, Séminaire de la Chaire Co-operators en analyse des risques actuariels, UQAM, Montréal, Canada (QC), 1er mai 2023.
  • Individual Claims Reserving Using Activation Patterns, Séminaire de la Chaire Co-operators en analyse des risques actuariels, UQAM, Montréal, Canada (QC), 1er avril 2022.

Enseignement

Démonstrations

Autres

  • Membre du Comité Conseil Permanent sur l’Éducation Inclusive (CCPEI) de l’UQAM (2022, 2023, 2024)
  • Co-organisatrice du séminaire d’été pour étudiants en actuariat et statistiques à l’UQAM (2021, 2023)
  • Membre du comité organisateur du Quantact SummerDay (2022)