no code implementations • 23 Mar 2024 • Samuel Stocksieker, Denys Pommeret, Arthur Charpentier
This paper aims to fill this gap by examining the specific challenges posed by data imbalance in self-supervised learning in the domain of tabular data, with a primary focus on autoencoders.
1 code implementation • 12 Feb 2024 • Agathe Fernandes Machado, Arthur Charpentier, Emmanuel Flachaire, Ewen Gallic, François Hu
The assessment of binary classifier performance traditionally centers on discriminative ability using metrics, such as accuracy.
1 code implementation • 29 Jan 2024 • Agathe Fernandes Machado, François Hu, Philipp Ratz, Ewen Gallic, Arthur Charpentier
Driven by an increasing prevalence of trackers, ever more IoT sensors, and the declining cost of computing power, geospatial information has come to play a pivotal role in contemporary predictive models.
no code implementations • 20 Nov 2023 • Mulah Moriah, Franck Vermet, Arthur Charpentier
The non-life insurance sector operates within a highly competitive and tightly regulated framework, confronting a pivotal juncture in the formulation of pricing strategies.
no code implementations • 31 Oct 2023 • François Hu, Philipp Ratz, Arthur Charpentier
Algorithmic fairness has gained prominence due to societal and regulatory concerns about biases in Machine Learning models.
1 code implementation • 12 Sep 2023 • François Hu, Philipp Ratz, Arthur Charpentier
Our approach seamlessly extends to approximate fairness, enveloping a framework accommodating the trade-off between risk and unfairness.
1 code implementation • 22 Aug 2023 • Philipp Ratz, François Hu, Arthur Charpentier
Ensuring trust and accountability in Artificial Intelligence systems demands explainability of its outcomes.
no code implementations • 5 Aug 2023 • Samuel Stocksieker, Denys Pommeret, Arthur Charpentier
In this paper, we propose a data augmentation procedure, the GOLIATH algorithm, based on kernel density estimates which can be used in classification and regression.
no code implementations • 23 Jun 2023 • Félix Foutel-Rodier, Arthur Charpentier, Hélène Guérin
The analysis of the model's equilibria reveals a criterion for the existence of an endemic equilibrium, which depends on the rate of immunity loss and the distribution of time between booster doses.
1 code implementation • 22 Jun 2023 • Arthur Charpentier, François Hu, Philipp Ratz
Given that such discrimination can often be attributed to historical data biases, an elimination or at least mitigation is desirable.
1 code implementation • 16 Jun 2023 • François Hu, Philipp Ratz, Arthur Charpentier
Algorithmic Fairness is an established field in machine learning that aims to reduce biases in data.
1 code implementation • 18 Feb 2023 • Samuel Stocksieker, Denys Pommeret, Arthur Charpentier
In this work, we consider the problem of imbalanced data in a regression framework when the imbalanced phenomenon concerns continuous or discrete covariates.
1 code implementation • 18 Jan 2023 • Arthur Charpentier, Emmanuel Flachaire, Ewen Gallic
Here, we will have the dual view: doing an intervention, or changing the treatment (even just hypothetically, in a thought experiment, for example by asking what would have happened if a person had been Black) can have an impact on the values of x.
no code implementations • 19 Dec 2022 • Arthur Charpentier
The analysis of discrimination has long interested economists and lawyers.
no code implementations • 3 Jul 2022 • Menna Hassan, Nourhan Sakr, Arthur Charpentier
This paper designs a sequential repeated game of a micro-founded society with three types of agents: individuals, insurers, and a government.
no code implementations • 17 May 2022 • Laurence Barry, Arthur Charpentier
Since the beginning of their history, insurers have been known to use data to classify and price risks.
no code implementations • 24 Feb 2022 • Vincent Grari, Arthur Charpentier, Marcin Detyniecki
In this paper, we will show that (2) this can be generalized to multiple pricing factors (geographic, car type), (3) it perfectly adapted for a fairness context (since it allows to debias the set of pricing components): We extend this main idea to a general framework in which a single whole pricing model is trained by generating the geographic and car pricing components needed to predict the pure premium while mitigating the unwanted bias according to the desired metric.
1 code implementation • 10 Aug 2021 • Amadou Barry, Karim Oualkacha, Arthur Charpentier
The fixed-effects model estimates the regressor effects on the mean of the response, which is inadequate to summarize the variable relationships in the presence of heteroscedasticity.
1 code implementation • 5 Jul 2021 • Arthur Charpentier, Lariosse Kouakou, Matthias Löwe, Philipp Ratz, Franck Vermet
In this paper, describe and analyse such a P2P product, with some reciprocal risk sharing contracts.
1 code implementation • 5 Mar 2021 • Michel Denuit, Arthur Charpentier, Julien Trufin
Theoretically, it is shown that it implements the autocalibration concept in pure premium calculation and ensures that balance also holds on a local scale, not only at portfolio level as with existing bias-correction techniques.
no code implementations • 8 Feb 2021 • Arthur Charpentier, Alfred Galichon, Marc Henry
We revisit Machina's local utility as a tool to analyze attitudes to multivariate risks.
no code implementations • 22 Mar 2020 • Arthur Charpentier, Romuald Elie, Carl Remlinger
As in multi-armed bandit problems, when an agent picks an action, he can not infer ex-post the rewards induced by other action choices.