applied-ml

Why we included this project

applied-ml is a hand-curated collection of papers, engineering blog posts, and conference talks where companies like Airbnb, Uber, Netflix, and Google explain how they actually build and run machine learning systems. Instead of theory, each entry is a real-world account: how the team framed the problem, which techniques worked, which ones flopped, and what results they got. That makes it a practical starting point for engineers and tech leads about to design a recommendation, forecasting, search, or data-quality pipeline who want to learn from organizations that already solved similar problems. The entries are grouped by topic, from data quality and feature stores to NLP, computer vision, and MLOps, so you can jump straight to the area you are working on. It is a reading list rather than runnable software, but for learning how production ML is actually done, it is hard to beat.