Tag Archives: ESSEC

Balance and Calibration of Probabilistic Scores: From GLM to Machine Learning

Tomorrow, I will give a talk on “Balance and Calibration of Probabilistic Scores:“” From GLM to Machine Learning” at Singapore campus – ESSEC Asia-Pacific. The abstract is

This study evaluates binary classifier performance with a focus on calibration, which is often overlooked by traditional metrics like accuracy. In high-stakes domains such as finance and healthcare, well-calibrated probabilities are crucial. We highlight the limitations of standard calibration metrics, particularly under score distortions and heterogeneous distributions. To address this, we introduce the Local Calibration Score and advocate optimizing models using Kullback-Leibler (KL) divergence to better align predicted scores with true probabilities. Our approach emphasizes balancing global and local calibration, ensuring overall distributional alignment while maintaining reliability across different score ranges. Using Random Forest and XGBoost across diverse datasets, we show that KL-based tuning improves calibration without sacrificing performance. Our results reveal that relying solely on traditional metrics can mislead model assessment, especially in sensitive decision-making scenarios. This is some joint work with Agathe Fernandes Machado and Ewen Gallic.

Modeling and Understanding Indirect Discrimination in Algorithmic Fairness

In a couple of days, I will give a talk on “Modeling and Understanding Indirect Discrimination in Algorithmic Fairness” at Singapore campus – ESSEC Asia-Pacific. The abstract is

Observed disparities between groups in algorithmic decisions (whether in hiring, credit approval, or risk prediction) do not necessarily imply direct discrimination. They may also stem from legitimate differences in the distribution of explanatory attributes. Understanding and quantifying which components of these gaps are “explained” versus those that reflect direct or indirect discrimination lies at the core of modern causal approaches to algorithmic fairness. This talk will begin with an accessible introduction to group-gap decomposition, building on the classical Kitagawa–Oaxaca–Blinder econometric framework. This approach separates differences attributable to observable characteristics from residual components that may signal discriminatory effects. The second part will introduce recent developments leveraging optimal transport to construct individual-level counterfactuals, enabling estimation of direct and indirect causal effects for each observation. In particular, we will show how sequential transport mappings aligned with a causal graph can disentangle pathways and quantify the contribution of each mediator. This methodology overcomes limitations of traditional linear models, introduced by Kitagawa, Oaxaca and Blinder, provides interpretable counterfactuals, and is well suited to complex empirical settings. The presentation will combine intuitive motivation, illustrative examples, and recent research insights, with the goal of making these tools accessible and useful to researchers in management science, applied economics, and data science.

On my way to Singapore

By the end of the week, I will be in Singapore. I plan to spend some time at the 40th Annual AAAI Conference on Artificial Intelligence, where Bertille Tierny and François Hu will give talks (in the “main track” and in the “student track”) to present our recent work, “Decomposing Direct and Indirect Biases in Linear Models under Demographic Parity Constraint“.

Then I will spend two weeks, invited at ESSEC Asia-Pacific, invited by Pierre Alquier. A couple of talks are also scheduled.

 

Talk at the ESSEC Risk Seminar

Thursday, I will be at La Défense, in Paris (France), to give a talk at the ESSEC Risk Seminar, entitled Causal Inference and Counterfactuals with Optimal Transport, with Applications in Fairness and Discrimination. Slides are now available, and the talk will be based on same recent papers, starting with Mitigating Discrimination in Insurance with Wasserstein Barycenters (presented last week-end at BIAS 2023) but also Fairness in Multi-Task Learning via Wasserstein Barycenters, and A Sequentially Fair Mechanism for Multiple Sensitive Attributes. There is also the textbook that should appear before the winter.

Talk on tail dependence in solvency II at ESSEC

I will be giving a talk at ESSEC (in La Défense) on Thursday morning, on “extremes and dependence in the context of Solvency II for insurance companies“. Slides are already available here.

With Solvency II, insurance companies need to get a better understanding about correlations between different lines of business, especially when about extremal correlation since the interest is about solvency.
For instance, QIS3 reports explains that
“In view of the insufficiency of currently available data, the setting of these correlation coefficients will necessarily include a certain degree of judgment. This is also true because, when selecting correlation coefficients, allowance should be made for non-linear tail correlation, which is not captured under a ?pure? linear correlation approach. To allow for this, the correlations used should be higher than simple analysis of relevant data would indicate.”
In this talk will discuss tail dependence, and the link between tail dependence and risk measures of aggregate risks.

At the same time, in Rennes, Benoît le Maux will be presenting our paper on “insuring natural catastrophes: should government intervene ?“. Since the work is still in progress, and not submited, I will not upload the slides… but the paper should be finished soon.