<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Projects on Ruize Jin | Data Scientist &amp; AI Engineer</title><link>https://www.ruizejin.com/projects/</link><description>Recent content in Projects on Ruize Jin | Data Scientist &amp; AI Engineer</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 01 Sep 2025 00:00:00 -0400</lastBuildDate><atom:link href="https://www.ruizejin.com/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>Interpretable Multi-Task Insurance Pricing</title><link/><pubDate>Mon, 01 Sep 2025 00:00:00 -0400</pubDate><guid/><description>&lt;p&gt;Built an interpretable PyTorch multi-task neural additive model using shared feature subnetworks to jointly predict claim frequency and severity on freMTPL data. Evaluated the model with six-fold cross-validation against GLM, GBM, and single-task NAM benchmarks.&lt;/p&gt;</description></item><item><title>NYC Taxi Mobility Intelligence</title><link/><pubDate>Sat, 01 Mar 2025 00:00:00 -0500</pubDate><guid/><description>&lt;p&gt;An interactive pre-trip prediction system for NYC Yellow Taxi rides. Given a pickup location, destination, and departure time, the system estimates travel time and pre-tip trip cost using a leakage-safe, temporally validated machine-learning pipeline.&lt;/p&gt;</description></item></channel></rss>