engineer1999/a-curated-list-of-ml-system-design-case-studies

This repository is a reference collection of over 300 real-world case studies showing how companies use machine learning in their products. Each entry links to a blog post, paper, or article written by engineers at the company, describing how they built a specific ML-powered feature or system. The companies involved include large names like Netflix, Airbnb, Stripe, Uber, Pinterest, and Walmart, as well as many others across industries including fintech, e-commerce, healthcare, and social platforms. The case studies are organized as a large table with columns for the company name, industry, a short description of what the ML system does, a link to the original article, and the year it was published. The topics covered are varied: some entries are about fraud detection, some about recommendation systems that suggest products or content, some about search ranking, some about natural language processing features, and some about forecasting demand or user behavior. Each case study represents a system that was actually built and deployed, not a research prototype. The intended audience is people who want to understand how machine learning works in practice at real companies, particularly those preparing for ML engineering or data science roles where system design knowledge is tested. Reading through these case studies gives concrete examples of the decisions companies make when deploying models: how they define the problem, what data they use, how they evaluate whether the model is working, and how the system integrates with existing products. This is a reference document, not software you run. The repository is updated over time as new case studies are added. The full table is very long, covering hundreds of entries across dozens of companies. The full README is longer than what was shown.