Skip to content
Instant download · PDF + web edition · Free sample of every book · 30-day refund promise
Latent Library Browse books
AI Engineering

Recommender Systems in Practice

From Simple Rules to Learned Rankings

Pages
81
Chapters
54
Level
Intermediate
Format
E-book

About this book

Recommendations drive what people watch, read and buy. This book explains how recommender systems work and how to build one that serves both users and the business.

You will start with simple baselines such as popularity and co-occurrence, then build collaborative filtering, matrix factorisation, content-based and embedding-based approaches, and two-stage retrieval and ranking. Chapters on evaluation cover offline metrics and online experiments, and later chapters tackle cold start, diversity, feedback loops and the ethics of optimising for engagement.

Worked examples use small datasets you can compute by hand.

What you will learn

  • Baselines that are surprisingly hard to beat
  • Collaborative filtering and matrix factorisation
  • Content-based and embedding-based recommendation
  • Two-stage retrieval and ranking architectures
  • Offline metrics, A/B tests and what they miss
  • Cold start, diversity, feedback loops and responsible design

Table of contents

  1. IntroductionIntroduction
  2. Chapter 1What Recommenders Do
  3. Chapter 2The Data: Users, Items and Interactions
  4. Chapter 3Explicit and Implicit Feedback
  5. Chapter 4Defining the Objective
  6. Chapter 5Baselines That Are Hard to Beat
  7. Chapter 6Co-occurrence and Association Rules
  8. Chapter 7Recency, Popularity and Time
  9. Chapter 8User-Based Collaborative Filtering
  10. Chapter 9Item-Based Collaborative Filtering
  11. Chapter 10Matrix Factorisation
  12. Chapter 11Content-Based Recommendation
  13. Chapter 12Embedding-Based Recommendation
  14. Chapter 13Hybrid Approaches
  15. Chapter 14Sequential and Session-Based Recommendation
  16. Chapter 15Context-Aware Recommendation
  17. Chapter 16Knowledge and Constraints
  18. Chapter 17The Two-Stage Architecture
  19. Chapter 18Candidate Generation
  20. Chapter 19Ranking Models
  21. Chapter 20Features for Ranking
  22. Chapter 21Position Bias
  23. Chapter 22Re-Ranking for Diversity and Rules
  24. Chapter 23Real-Time Serving
  25. Chapter 24Recommendation and Search
  26. Chapter 25Offline Evaluation
  27. Chapter 26NDCG, Worked Through
  28. Chapter 27Beyond Accuracy: Coverage, Novelty and Diversity
  29. Chapter 28Why Offline Metrics Mislead
  30. Chapter 29Online Experiments
  31. Chapter 30Interleaving
  32. Chapter 31Long-Term Effects
  33. Chapter 32Business Metrics
  34. Chapter 33Evaluation Checklist
  35. Chapter 34Logging: The Data Pipeline Behind Recommendations
  36. Chapter 35Matrix Factorisation, One Step at a Time
  37. Chapter 36Item-Based Recommendations in Code
  38. Chapter 37Recommendations in Email and Notifications
  39. Chapter 38Business-to-Business and Long Purchase Cycles
  40. Chapter 39Language Models in Recommender Systems
  41. Chapter 40Team, Process and Governance
  42. Chapter 41Approximate Nearest-Neighbour Search
  43. Chapter 42Debugging a Recommender
  44. Chapter 43Cold Start
  45. Chapter 44Exploration and Exploitation
  46. Chapter 45Feedback Loops and Filter Bubbles
  47. Chapter 46Fairness for Users and Providers
  48. Chapter 47Privacy
  49. Chapter 48Explanations
  50. Chapter 49User Control
  51. Chapter 50Content Quality and Safety
  52. Chapter 51Case Study: An Online Bookshop
  53. Chapter 52Case Study: A Streaming Service
  54. Chapter 53Case Study: A Job Board
  55. Chapter 54A Project Checklist
  56. AppendixExercises
  57. GlossaryGlossary

Who this book is for

Engineers, data scientists and product managers working on personalisation and recommendations.

Details

FormatPDF + web edition
Length81 pages (approx.)
Chapters54
LevelIntermediate
LanguageEnglish
TopicAI Engineering
AuthorLatent Library Editorial

Keep reading

You may also like

All books
$12.99
Details