Implementing and designing systems that make suggestions to users are among the most popular and essential machine learning applications available. Whether you want customers to find the most appealing items at your online store, videos to enrich and entertain them, or news they need to know, recommendation systems (RecSys) provide the way. In this practical book, authors Bryan Bischof and Hector Yee illustrate the core concepts and examples to help you create a RecSys for any industry or scale. You'll learn the math, ideas, and implementation details you need to succeed. This book includes the RecSys platform components, relevant MLOps tools in your stack, plus code examples and helpful suggestions in PySpark, SparkSQL, FastAPI, and Weights & Biases. You'll learn:
Table of Contents
- Preface
- I. Warming Up
- 1. Introduction
- 2. User-Item Ratings and Framing the Problem
- 3. Mathematical Considerations
- 4. System Design for Recommending
- 5. Putting It All Together: Content Based Recommender
- II. Retrieval
- 6. Data Processing
- 7. Serving Models and Architectures
- 8. Putting It All Together: Data Processing and Counting Recommender
- III. Ranking
- 9. Feature based and counting-based recommendations
- 10. Low Rank Methods
- 11. Personalized Recommendation Metrics
- 12. Training for Ranking
- 13. Putting It All Together: Experimenting and Ranking
- IV. Serving
- 14. Business Logic
- 15. Bias in Recommendation Systems
- 16. Acceleration Structures
- V. The Future of Recs
- 17. Sequential Recommenders
- 18. What’s Next for Recs?
- About the Authors