<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Projects on Jean-Baptiste Attié</title><link>https://jibeyjb.github.io/projects/</link><description>Recent content in Projects on Jean-Baptiste Attié</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 01 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jibeyjb.github.io/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>Le Carnet de Prépa — Launching an E-commerce Product End-to-End</title><link>https://jibeyjb.github.io/projects/le-carnet-de-prepa/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://jibeyjb.github.io/projects/le-carnet-de-prepa/</guid><description>Designed, produced and sold a physical study notebook for French prépa students. Full-stack e-commerce site built with Claude Code, automated Stripe-to-print-on-demand pipeline, Meta Ads. 340+ sales and €9,000 revenue in one year.</description></item><item><title>Credit Default Prediction — Crédit Agricole Personal Finance &amp; Mobility</title><link>https://jibeyjb.github.io/projects/credit-default-scoring/</link><pubDate>Thu, 01 Oct 2026 00:00:00 +0000</pubDate><guid>https://jibeyjb.github.io/projects/credit-default-scoring/</guid><description>Machine learning model (logistic regression, gradient boosting) estimating customers&amp;rsquo; probability of default on a 30-million-row dataset, plus a SAS-to-Snowflake database migration for pipeline automation.</description></item><item><title>Entropy Methods for the Fractional Porous Medium Equation — Johns Hopkins University</title><link>https://jibeyjb.github.io/projects/johns-hopkins-edp/</link><pubDate>Wed, 14 Aug 2024 00:00:00 +0000</pubDate><guid>https://jibeyjb.github.io/projects/johns-hopkins-edp/</guid><description>Six-month research stay at the Johns Hopkins Department of Mathematics. Proved an exponential convergence rate toward the stationary profile using entropy methods, and wrote the research report in LaTeX.</description></item><item><title>Neural Networks for High-Gradient Functions — Research Apprenticeship at I2M</title><link>https://jibeyjb.github.io/projects/neural-networks-i2m/</link><pubDate>Thu, 01 Jun 2023 00:00:00 +0000</pubDate><guid>https://jibeyjb.github.io/projects/neural-networks-i2m/</guid><description>Research work-study at the Institut de Mathématiques de Marseille: neural network theory, TensorFlow experiments, and a gradient-aware sampling method that improves approximation where the target function varies sharply.</description></item><item><title>Automating MT-191 Billing Processing — Natixis</title><link>https://jibeyjb.github.io/projects/natixis-billing-automation/</link><pubDate>Wed, 15 Jan 2025 00:00:00 +0000</pubDate><guid>https://jibeyjb.github.io/projects/natixis-billing-automation/</guid><description>Custom VBA tool that extracts, transforms and visualizes MT-191 billing data for the Cash Management team. Built from business users&amp;rsquo; requirements; processing time cut from 2 hours to 3 minutes.</description></item></channel></rss>