Category Archives: Conferences

Decomposing Direct and Indirect Biases in Linear Models under Demographic Parity Constraint

Our paper “Decomposing Direct and Indirect Biases in Linear Models under Demographic Parity Constraint“, with Bertille Tierny and François Hu is now online on ArXiv.

Linear models are widely used in high-stakes decision-making due to their simplicity and interpretability. Yet when fairness constraints such as demographic parity are introduced, their effects on model coefficients, and thus on how predictive bias is distributed across features, remain opaque. Existing approaches on linear models often rely on strong and unrealistic assumptions, or overlook the explicit role of the sensitive attribute, limiting their practical utility for fairness assessment. We extend the work of (Chzhen and Schreuder, 2022) and (Fukuchi and Sakuma, 2023) by proposing a post-processing framework that can be applied on top of any linear model to decompose the resulting bias into direct (sensitive-attribute) and indirect (correlated-features) components. Our method analytically characterizes how demographic parity reshapes each model coefficient, including those of both sensitive and non-sensitive features. This enables a transparent, feature-level interpretation of fairness interventions and reveals how bias may persist or shift through correlated variables. Our framework requires no retraining and provides actionable insights for model auditing and mitigation. Experiments on both synthetic and real-world datasets demonstrate that our method captures fairness dynamics missed by prior work, offering a practical and interpretable tool for responsible deployment of linear models.

On sera à Singapour pour le présenter fin janvier, à AAAI 2026, 40th Annual AAAI Conference on Artificial Intelligence.

GCKE 2025, Osaka, Annual Global Congress of Knowledge Economy

This week, I will attend the 10th Annual Global Congress of Knowledge Economy, in Osaka (大阪). On Wednesday morning, I will chair the GCKE04 session, Economic Governance & Sustainable Development. I will also give a talk on “Fairness and Insurance: Disentangling Illegitimate and Indirect Discriminations” (slides are available). It is based on recent work with Oliver and Marie-Pier Côté.

2025 CAS (Casualty Actuarial Science) Canada Connection

In less than a month, Olivier Côté will attend the  CAS Canada Connection, in Toronto.  He will speak in a session Operationalizing Fairness in Actuarial Pricing: From Principle to Practice

Fairness metrics often lack actuarial relevance and are expressed in abstract units, obscuring real-world consequences. For actuaries to intervene, proxy effects and unfair biases must be quantified in insurance-relevant terms: dollars and people. This session will present new research from the CAS Race and Insurance Pricing series, focusing on the unique challenge of establishing fairness in actuarial pricing. We argue that actuarial fairness, solidarity, and causality form the three dimensions of fairness in insurance. These give rise to a five-point spectrum of pricing benchmarks, each reflecting distinct fairness goals and trade-offs. We quantify the monetary impact of unfairness at both the policyholder and segment levels through a large-scale Québec auto insurance case study.

Learning objectives are (1) Describe three dimensions of fairness in insurance pricing: actuarial fairness, solidarity, and causality (2) Translate these dimensions of fairness into a spectrum of five pricing benchmarks (3) Diagnose and quantify potential unfairness at both individual and segment levels using actuarially meaningful metrics.

It will be based on our recent paper, A Scalable toolbox for exposing indirect discrimination in insurance rates”.

Certitudes collectives et incertitudes individuelles, les données massives changent-elles la donne ?

Il y a un peu plus d’un an, je participais aux rencontres de Cerisy, et on m’avait demandé de mettre par écrit mon intervention orale. C’est maintenant chose faite… avec comme titre Certitudes collectives et incertitudes individuelles, les données massives changent-elles la donne ?

Depuis plus de deux siècles, les sciences sociales se heurtent à un paradoxe tenace : si les comportements individuels sont incertains, contingents et souvent imprévisibles, leur agrégation produit des régularités collectives d’une étonnante stabilité. De Quetelet à Durkheim, en passant par Weber, cette tension entre incertitude individuelle et certitude collective a nourri la constitution même d’une science sociale quantitative. L’ère des données massives redonne une actualité brûlante à ce paradoxe. Jamais les sociétés humaines n’ont généré autant de traces numériques : achats, communications, déplacements, interactions en ligne, données physiologiques. Ces flux continus, enregistrés et analysés à grande échelle, alimentent l’espoir d’une prévisibilité quasi totale. Certains annoncent la fin de l’incertitude : les algorithmes sauraient anticiper nos choix de consommation, les crises sanitaires ou les évolutions politiques. Mais cette promesse soulève des questions épistémologiques et sociales profondes : que signifie appliquer une probabilité à un événement singulier ? Jusqu’où un score algorithmique peut-il être considéré comme fiable, juste ou légitime ? L’objectif de ce texte est d’examiner, à nouveaux frais, le rapport entre incertitude individuelle et certitude collective à l’ère du big data. Pour ce faire, nous parcourrons plusieurs étapes : d’abord, revenir aux fondements historiques de la découverte des régularités collectives ; ensuite, montrer comment la rationalité limitée, loin de contredire la prévisibilité, contribue à l’émergence de modèles robustes ; puis analyser les débats contemporains sur l’interprétation des probabilités et la nécessité de calibrer les scores ; enfin, explorer la dimension temporelle de la prévision, du nowcasting instantané aux projections climatiques de long terme. Notre thèse est que les données massives ne résolvent pas le paradoxe, mais en amplifient la portée et les enjeux. Elles déplacent le débat d’un plan strictement scientifique vers un plan éthique et politique : comment gouverner l’incertitude, dans un monde où elle est à la fois plus visible, plus mesurable, mais aussi plus contestable ?

La suite est en ligne sur https://hal.science/hal-05250596

IJCAI 2025 Workshop on Explainable Artificial Intelligence (XAI)

This week, Marouane will present recent work at the Workshop on Explainable Artificial Intelligence (XAI), at IJCAI in Montréal,

Explainable Artificial Intelligence (XAI) addresses the challenge of how to communicate and explain the decision-making of AI systems. The need for explainability increases as AI systems are deployed in critical applications, raising questions such as: how should explainable AI systems be designed? What queries should AI systems be able to answer about their models and decisions? How should user interfaces communicate decision making? What types of user interactions should be supported? And how should explanation quality be assessed?

The Explainable AI (XAI) workshop at IJCAI provides a forum for discussing recent research on XAI methods, highlighting and documenting promising approaches, and encouraging further work, thereby fostering connections among researchers interested in AI, human-computer interaction, and cognitive theories of explanation and transparency. This topic is of particular importance but not limited to machine learning, AI planning, and knowledge reasoning & representation.

In addition to encouraging descriptions of original or recent contributions to XAI (i.e., theory, simulation studies, subject studies, demonstrations, applications), we will welcome contributions that: survey related work; describe key issues that require further research; or highlight relevant challenges of interest to the AI community and plans for addressing them.

The paper, Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models, is available on ArXiv.

Actuarial Research Conference in Toronto

From Tuesday to Friday, I will attend the 60th Actuarial Research Conference in Toronto. With Olivier and Marie-Pier Côté, we will give a series of talk on fairness and discrimination.

  • I will talk in an Invited Session on Artificial Intelligence in Insurance (as well as Marie-Pier Côté)
  • Olivier Côté will present in Session 1 – Bias in Assessing Financial Risk
  • With Olivier and Marie-Pier, we will present in one of the Casualty Actuarial Society Sponsored Sessions, Session 1A Scalable Toolbox for Exposing Indirect Discrimination in Insurance Rates

KNN and K-means in Gini Prametric Spaces, at ECAI 2025, in Bologna, Italy

Our paper, written with Cassandra Mussard, intern last summer, and Stéphane Mussard, entitled KNN and K-means in Gini Prametric Spaces will be presented this Fall at the 28th European Conference on Artificial Intelligence, ECAI 2025, that will take place on October 25-30, 2025, in Bologna, Italy.

This paper introduces innovative enhancements to the K-means and K-nearest neighbors (KNN) algorithms based on the concept of Gini prametric spaces. Unlike traditional distance metrics, Gini-based measures incorporate both value-based and rank-based information, improving robustness to noise and outliers. The main contributions of this work include: proposing a Gini-based measure that captures both rank information and value distances; presenting a Gini K-means algorithm that is proven to converge and demonstrates resilience to noisy data; and introducing a Gini KNN method that performs competitively with state-of-the-art approaches such as Hassanat’s distance in noisy environments. Experimental evaluations on 14 datasets from the UCI repository demonstrate the superior performance and efficiency of Gini-based algorithms in clustering and classification tasks. This work opens new avenues for leveraging rank-based measures in machine learning and statistical analysis.

Causalité, pour l’Institut des Actuaires, Paris

Ce mardi, je participe en visio à la conférence annuelle de l’Institut des Actuaires, à Paris, pour une session sur les modèles causaux en assurance, avec une introduction générale, avant qu’Aurélien Couloumy ne prenne la suite pour présenter des applications.

Pour ceux qui veulent un exercice pour l’été, je peux mentionner un tableau tiré de “Optimum Strategies for Creativity and Longevity

Si quelqu’un arrive à établir un lien causal, je suis intéressé.

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models

Our paper Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models, with Marouane Il Idrissi and Agathe Fernandes Machado, is now online. It will be presented at the IJCAI 2025 Workshop on Explainable Artificial Intelligence (XAI), in Montréal this Summer…

Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient allocations, the Weber and Harsanyi sets, that extend beyond Shapley values and offer richer interpretative flexibility. We present an accessible overview of these allocation schemes, clarify the distinction between value functions and aggregation rules, and introduce a three-step blueprint for constructing reliable and theoretically-grounded feature attributions. Our goal is to move beyond fixed axioms and provide the XAI community with a coherent framework to design attribution methods that are both meaningful and robust to shifting methodological trends.

Conference in Montpellier (France), on calibration

This morning, I will present at the “quatrième Journée d’Econometrie appliquée, en l’honneur de Michel Terraza”. I will present recent work with Agathe Fernandes Machado, Ewen Gallic, François Hu, and Emmanuel Flachaire. Slides are available. The talk is on “Calibration, ou interprétation probabiliste des scores de modèles boites noires” (Calibration, or probabilistic interpretationof black box model scores, but slides are in English).

Confidence and Fairness: Scientific Foundations in AI and Risk, Workshop in Paris

Tomorrow, we organize our workshop Confidence and Fairness: Scientific Foundations in AI and Risk, at the SCOR headquarters, in Paris. I’m going to give the keynote address for the day, presenting the work we’ve been able to carry out over the past 18 months (over the 3 years of funding), while laying the foundations for the concepts we’ll be discussing throughout the day.


9:00 – Registration
9:20 – Introduction speech
9:30 – Arthur Charpentier – “Fairness of predictive models: an application to insurance markets
10:15 – Coffee break
10:45 – Toon Calders – “Unfair, You Say? Explain Yourself!”
11:30 – Isabel Valera – “Society-centered AI: An Integrative Perspective on Algorithmic Fairness”
12:15 – Lunch break
13:15 – Jean Michel Loubes – “Beyond fairness measures, discovering the bias in the algorithm”
14:00 – Evgeny Chzhen – “An optimization approach to post-processing for classification with system constraints”
14:45 – Michele Loi – “From Facts to Fairness: Diagnostic Models in Algorithmic Decision-Making”
15:30 – Coffee break
16:00 – Aurélie Lemmens – “Fair Active Learning for Personalized Policies”
16:45 – François Hu and Antoine Ly – “Fairness and Confidence in Insurance Markets, a Practitioners Perspective”
17:30 – Closing cocktail

Optimal Transport on Categorical Data for Counterfactuals, at IJCAI’25

This summer, Agathe will present our recent paper Optimal Transport on Categorical Data for Counterfactuals using Compositional Data and Dirichlet Transport at the 34th International Joint Conference on Artificial Intelligence, IJCAI.

Recently, optimal transport-based approaches have gained attention for deriving counterfactuals, e.g., to quantify algorithmic discrimination. However, in the general multivariate setting, these methods are often opaque and difficult to interpret. To address this, alternative methodologies have been proposed, using causal graphs combined with iterative quantile regressions (Plečko and Meinshausen (2020)) or sequential transport (Fernandes Machado et al. (2025)) to examine fairness at the individual level, often referred to as “counterfactual fairness.” Despite these advancements, transporting categorical variables remains a significant challenge in practical applications with real datasets. In this paper, we propose a novel approach to address this issue. Our method involves (1) converting categorical variables into compositional data and (2) transporting these compositions within the probabilistic simplex of \mathbb{R}^d. We demonstrate the applicability and effectiveness of this approach through an illustration on real-world data, and discuss limitations.

Mesurer et corriger les biais dans les systèmes d’IA

Ce midi, je participerai (en ligne) aux lundis de l’IA et de la finance, avec comme thème “mesurer et corriger les biais dans les systèmes d’IA”, dans le cadre d’un séminaire co-organisé par l’Autorité de Contrôle Prudentiel et de Résolution (ACPR/Banque de France) et Télécom Paris. Mon intervention, en ouverture, reviendra sur l’équité dans le contexte de l’assurance [les slides sont disponibles].

Continue reading Mesurer et corriger les biais dans les systèmes d’IA

Confidence and Fairness: Scientific Foundations in AI and Risk (mid-May in Paris)

Mid-May, we organize, with the SCOR Foundation for Science a one-day workshop on Confidence and Fairness, Scientific Foundations in AI and Risk. Registrations are now open ! The agenda will be

9:00 registration
9:20 – introduction speach
9:30 – Arthur Charpentier
10:15 coffee break
10:45 – Toon Calders
11:30 – Isabel Valera
12:15 lunch break
13:15 – Jean Michel Loubes
14:00 – Evgeny Chzhen
14:45 – Michele Loi
15:30 coffee break
16:00 – Aurélie Lemmens
16:45 – François Hu and Antoine Ly
17:30 – closing cocktail