<?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 Eiken</title><link>https://eiken59.github.io/projects/</link><description>Recent content in Projects on Eiken</description><generator>Hugo -- 0.147.2</generator><language>en</language><lastBuildDate>Mon, 22 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://eiken59.github.io/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>The Gambler's Ruin Problem for One-Dimensional Random Walks</title><link>https://eiken59.github.io/projects/gamblers-ruin/</link><pubDate>Mon, 22 Dec 2025 00:00:00 +0000</pubDate><guid>https://eiken59.github.io/projects/gamblers-ruin/</guid><description>An expository study of hitting probabilities for one-dimensional random walks — from the simple symmetric walk to bounded and finite-variance steps — using difference equations and martingale methods. Advised by Prof. Yuki Chino.</description></item><item><title>Credit Card Default Prediction Using Machine Learning</title><link>https://eiken59.github.io/projects/credit-default-ml/</link><pubDate>Sat, 19 Jul 2025 00:00:00 +0000</pubDate><guid>https://eiken59.github.io/projects/credit-default-ml/</guid><description>A supervised-learning study on an imbalanced 30,000-client dataset (~22% default), comparing five classifiers with a focus on minority-class performance rather than misleading accuracy. Course project at École polytechnique.</description></item></channel></rss>