<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LightFM on Hakan Ates</title><link>https://www.ateshakan.com/tags/lightfm/</link><description>Recent content in LightFM on Hakan Ates</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Hakan Ates</copyright><lastBuildDate>Wed, 20 Nov 2024 00:00:00 +0000</lastBuildDate><atom:link href="https://www.ateshakan.com/tags/lightfm/index.xml" rel="self" type="application/rss+xml"/><item><title>Rec4Dish — a menu recommender trained on real restaurant orders</title><link>https://www.ateshakan.com/projects/rec4dish/</link><pubDate>Wed, 20 Nov 2024 00:00:00 +0000</pubDate><guid>https://www.ateshakan.com/projects/rec4dish/</guid><description>A recommendation system for restaurant menus that beat the random baseline 3.5× (Precision@5 31.8% vs 9.2%) and held cold-start users at parity. Built end-to-end on real customer order data during a six-month software-engineering internship at Dishup SRL, an Italian restaurant-tech startup, and delivered as my MSc thesis at the University of Padua — “A Hybrid and Adaptive Learning Framework for Personalized Restaurant Recommendations”.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.ateshakan.com/projects/rec4dish/feature.png"/></item></channel></rss>