Blog

January 19, 2026 · 9 min read

How to work with AI

A set of best pratices on how to work and collaborate with AI to co-own your work

January 18, 2026 · 4 min read

Mimesis: training field interviews with personas

Mimesis is a web-based interview training platform. It allows master-level students and researchers to conduct realistic interviews with adaptive AI personas grounded in real interview data. The project combines two strong axes: rapid delivery using agentic AI coding practices, and deep conceptual work on persona design as a proxy for human social behavior.

August 1, 2025 · 5 min read

Moliere.love : traduire Molière en français moderne avec l’IA

Un projet expérimental mêlant intelligence artificielle et humanités numériques pour traduire les œuvres de Molière en français moderne, vers par vers. Conçu comme un laboratoire de travail avec les LLM, il explore le prompt engineering, la génération contrôlée de texte et les enjeux d’accessibilité, à travers une application web et mobile pensée pour un usage pédagogique réel.

August 1, 2024 · 3 min read

Early-Stage AI feasibility validation

Building something that works is no longer the hard part. Knowing whether it should exist is. This piece looks at two AI-heavy projects that never shipped, not because the technology failed, but because business reality intervened. From toxic content detection on TikTok to a PMF validation platform for solo founders, both experiments used AI to compress time-to-insight, test assumptions early, and expose strategic constraints fast. The focus is on how AI reshapes early-stage decision-making by making it cheaper to be wrong — and clearer when it’s time to move on.

November 10, 2023 · 3 min read

Who is Moliere mocking?

The enduring appeal of Molière's plays lies in their ability to serve as mirrors reflecting universal human flaws and shortcomings. The humor in Molière's characters, often perceived as mockery, actually prompts self-reflection and self-awareness, offering a form of absolution for common human imperfections.

October 4, 2023 · 10 min read

Rewriting Moliere plays with chatGPT

August 1, 2023 · 3 min read

Scaling Real-Time Global Taxi Pricing with AutoML at Karhoo

At Karhoo, I led pricing and forecasting for a global taxi marketplace operating in real time across multiple continents. Facing accuracy ceilings and scaling limits with bespoke scikit-learn random forest models, we benchmarked and migrated to Vertex AI AutoML on GKE, with feature pipelines in BigQuery and automated model promotion. The transition delivered significantly higher prediction performance, lower infrastructure and operational costs, built-in drift handling, and greater flexibility for global rollout under strict latency constraints.

October 21, 2019 · 2 min read

New statistical learning course on openclassroooms

I am very excited to announce that my new course on statistical learning is now available on openclassrooms.

February 15, 2019 · 3 min read

Teaching Data Science at UM6P

I had the chance to inaugurate the new Data Science and Industrial Processes curriculum launched in 2018 at the Emines school of industrial management

February 21, 2018 · 11 min read

Reduce GPU costs with startup scripts on the Google Cloud Engine

Deep Learning can be expensive. Use startup scripts to reduce virtual instance usage and lower costs. Reshape your workflow to maximize GPU based instances

February 6, 2018 · 6 min read

iPhone addiction? Get a grip!

My iPhone addiction was ruining my life. So I decided to fight back. Here are the 5 simple and easy tricks I've implemented to regain control.

January 1, 2018 · 13 min read

Top gsutil command lines to get started on Google Cloud Storage

Learn the best Google Cloud Storage features with these gsutil commands.

December 4, 2017 · 14 min read

AutoML on AWS

You can now build super efficient predictive analytics pipelines on AWS without a single line of code!

February 19, 2017 · 3 min read

Writing Effective Amazon Machine Learning

Writing a book is hard work. Here's how I did it for my book on the Amazon Machine Learning service.

March 16, 2016 · 7 min read

Large Data with Scikit-learn - Boston Meetup

Slides for the Boston Data Science Meetup on batch processing with scikit-learn

February 8, 2016 · 5 min read

Paris Meetup slides Topic Modeling of Twitter Followers

Topic Modeling of Twitter Followers

February 5, 2016 · 12 min read

Amazon Machine Learning: Nice and Easy or Overly Simple?

Amazon Machine Learning is a predictive analytics service with binary/multiclass classification and linear regression features. The service offers a simple workflow but lacks model selection features and has slow execution times. Predictive performances are satisfying.

November 19, 2015 · 6 min read

Dynamics of Debates with Time Maps

Timemaps are a simple way to visualize the frequency of events and can be used in NLP and to detect bots

November 12, 2015 · 1 min read

NLP Analysis of the 2015 presidential candidate debates

Summarization, sentiment analysis, topic modeling, all relevant NLP methods to analyze political debates.

September 16, 2015 · 12 min read

Segmentation of Twitter Timelines via Topic Modeling

Comparing LSA and LDA for topic modeling of a corpus of twitter followers.

September 4, 2015 · 10 min read

Topic Modeling of Twitter Followers

Topic modeling of twitter followers with Gensim and Latent Dirichlet Allocation with python 3 code.