13 citations · 24 across the 18 of their papers we have counts for
7 papers · 1 filter
Preventing RNN from Using Sequence Length as a Feature
Jean-Thomas Baillargeon, Hélène Cossette, Luc Lamontagne
Recurrent neural networks are deep learning topologies that can be trained to classify long documents. However, in our recent work, we found a critical problem with these cells: th…
A new method to construct high-dimensional copulas with Bernoulli and Coxian-2 distributions
Christopher Blier-Wong, Hélène Cossette, Sébastien Legros +1
We propose an approach to construct a new family of generalized Farlie-Gumbel-Morgenstern (GFGM) copulas that naturally scales to high dimensions. A GFGM copula can model moderate…
Collective risk models with FGM dependence
Christopher Blier-Wong, Hélène Cossette, Etienne Marceau
We study copula-based collective risk models when the dependence structure is defined by a Farlie-Gumbel-Morgenstern (FGM) copula. By leveraging a one-to-one correspondence between…
Individual Claims Reserving using Activation Patterns
Marie Michaelides, Mathieu Pigeon, Hélène Cossette
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 cla…
Efficient evaluation of risk allocations
Christopher Blier-Wong, Hélène Cossette, Etienne Marceau
Expectations of marginals conditional on the total risk of a portfolio are crucial in risk-sharing and allocation. However, computing these conditional expectations may be challeng…
Exchangeable FGM copulas
Christopher Blier-Wong, Hélène Cossette, Etienne Marceau
Copulas are a powerful tool to model dependence between the components of a random vector. One well-known class of copulas when working in two dimensions is the Farlie-GumbelMorgen…
Micro-level Reserving for General Insurance Claims using a Long Short-Term Memory Network
Ihsan Chaoubi, Camille Besse, Hélène Cossette +1
Detailed information about individual claims are completely ignored when insurance claims data are aggregated and structured in development triangles for loss reserving. In the hop…