Practical Recommender Systems

Table of contents

1. Copyright
2. Brief Table of Contents
3. Table of Contents
4. Preface
5. Acknowledgments
6. About this book
7. About the author
8. About the cover illustration
9. Part 1. Getting ready for recommender systems
   1. Chapter 1. What is a recommender?
      1. 1.1. Real-life recommendations
      2. 1.2. Taxonomy of recommender systems
      3. 1.3. Machine learning and the Netflix Prize
      4. 1.4. The MovieGEEKs website
      5. 1.5. Building a recommender system
      6. Summary
   2. Chapter 2. User behavior and how to collect it
      1. 2.1. How (I think) Netflix gathers evidence while you browse
      2. 2.2. Finding useful user behavior
      3. 2.3. Identifying users
      4. 2.4. Getting visitor data from other sources
      5. 2.5. The collector
      6. 2.6. What users in the system are and how to model them
      7. Summary
   3. Chapter 3. Monitoring the system
      1. 3.1. Why adding a dashboard is a good idea
      2. 3.2. Doing the analytics
      3. 3.3. Personas
      4. 3.4. MovieGEEKs dashboard
      5. Summary
   4. Chapter 4. Ratings and how to calculate them
      1. 4.1. User-item preferences
      2. 4.2. Explicit or implicit ratings
      3. 4.3. Revisiting explicit ratings
      4. 4.4. What are implicit ratings?
      5. 4.5. Calculating implicit ratings
      6. 4.6. How to implement implicit ratings
      7. 4.7. Less frequent items provide more value
      8. Summary
   5. Chapter 5. Non-personalized recommendations
      1. 5.1. What’s a non-personalized recommendation?
      2. 5.2. How to make recommendations when you have no data
      3. 5.3. Implementing the chart and the groundwork for the recommender system component
      4. 5.4. Seeded recommendations
      5. Summary
   6. Chapter 6. The user (and content) who came in from the cold
      1. 6.1. What’s a cold start?
      2. 6.2. Keeping track of visitors
      3. 6.3. Addressing cold-start problems with algorithms
      4. 6.4. Those who doesn’t ask, won’t know
      5. 6.5. Using association rules to start recommending things fast
      6. Summary
10. Part 2. Recommender algorithms
    1. Chapter 7. Finding similarities among users and among content
       1. 7.1. Why similarity?
       2. 7.2. Essential similarity functions
       3. 7.3. k-means clustering
       4. 7.4. Implementing similarities
       5. Summary
    2. Chapter 8. Collaborative filtering in the neighborhood
       1. 8.1. Collaborative filtering: A history lesson
       2. 8.2. Calculating recommendations
       3. 8.3. Calculating similarities
       4. 8.4. Amazon’s algorithm to precalculate item similarity
       5. 8.5. Ways to select the neighborhood
       6. 8.6. Finding the right neighborhood
       7. 8.7. Ways to calculate predicted ratings
       8. 8.8. Prediction with item-based filtering
       9. 8.9. Cold-start problems
       10. 8.10. A few words on machine learning terms
       11. 8.11. Collaborative filtering on the MovieGEEKs site
       12. 8.12. What’s the difference between association rule recs and collaborative recs?
       13. 8.13. Levers to fiddle with for collaborative filtering
       14. 8.14. Pros and cons of collaborative filtering
       15. Summary
    3. Chapter 9. Evaluating and testing your recommender
       1. 9.1. Business wants lift, cross-sales, up-sales, and conversions
       2. 9.2. Why is it important to evaluate?
       3. 9.3. How to interpret user behavior
       4. 9.4. What to measure
       5. 9.5. Before implementing the recommender...
       6. 9.6. Types of evaluation
       7. 9.7. Offline evaluation
       8. 9.8. Offline experiments
       9. 9.9. Implementing the experiment in MovieGEEKs
       10. 9.10. Evaluating the test set
       11. 9.11. Online evaluation
       12. 9.12. Continuous testing with exploit/explore
       13. Summary
    4. Chapter 10. Content-based filtering
       1. 10.1. Descriptive example
       2. 10.2. Content-based filtering
       3. 10.3. Content analyzer
       4. 10.4. Extracting metadata from descriptions
       5. 10.5. Finding important words with TF-IDF
       6. 10.6. Topic modeling using the LDA
       7. 10.7. Finding similar content
       8. 10.8. Creating the user profile
       9. 10.9. Content-based recommendations in MovieGEEKs
       10. 10.10. Evaluation of the content-based recommender
       11. 10.11. Pros and cons of content-based filtering
       12. Summary
    5. Chapter 11. Finding hidden genres with matrix factorization
       1. 11.1. Sometimes it’s good to reduce the amount of data
       2. 11.2. Example of what you want to solve
       3. 11.3. A whiff of linear algebra
       4. 11.4. Constructing the factorization using SVD
       5. 11.5. Constructing the factorization using Funk SVD
       6. 11.6. Doing recommendations with Funk SVD
       7. 11.7. Funk SVD implementation in MovieGEEKs
       8. 11.8. Explicit vs. implicit data
       9. 11.9. Evaluation
       10. 11.10. Levers to fiddle with for Funk SVD
       11. Summary
    6. Chapter 12. Taking the best of all algorithms: Implementing hybrid recommenders
       1. 12.1. The confused world of hybrids
       2. 12.2. The monolithic
       3. 12.3. Mixed hybrid recommender
       4. 12.4. The ensemble
       5. 12.5. Feature-weighted linear stacking (FWLS)
       6. 12.6. Implementation
       7. Summary
    7. Chapter 13. Ranking and learning to rank
       1. 13.1. Learning to rank an example at Foursquare
       2. 13.2. Re-ranking
       3. 13.3. What’s learning to rank again?
       4. 13.4. Bayesian Personalized Ranking
       5. 13.5. Implementation of BPR
       6. 13.6. Evaluation
       7. 13.7. Levers to fiddle with for BPR
       8. Summary
    8. Chapter 14. Future of recommender systems
       1. 14.1. This book in a few sentences
       2. 14.2. Topics to study next
       3. 14.3. What’s the future of recommender systems?
       4. 14.4. Final thoughts
11. Index
12. List of Figures
13. List of Tables
14. List of Listings