People who liked this talk also liked … Building Recommendation Systems Using Ruby

From Amazon, to Spotify, to thermostats, recommendation systems are everywhere. The ability to provide recommendations for your users is becoming a crucial feature for modern applications. In this talk I'll show you how you can use Ruby to build recommendation systems for your users. You don't need a PhD to build a simple recommendation engine -- all you need is Ruby. Together we'll dive into the dark arts of machine learning and you'll discover that writing a basic recommendation engine is not as hard as you might have imagined. Using Ruby I'll teach you some of the common algorithms used in recommender systems, such as: Collaborative Filtering, K-Nearest Neighbor, and Pearson Correlation Coefficient. At the end of the talk you should be on your way to writing your own basic recommendation system in Ruby.

Transcript

1. People who liked this talk also liked … Building Recommendation Systems Using Ruby Ryan Weald, @rweald LA RubyConf 2013 1
2. Who is this guy? What does he know about recommendation systems? 2
3. Data Scientist @Sharethrough Native advertising platform 3
5. Outline 1) What is a recommendation system? 2) Collaborative filtering based recommendations 3) Content based recommendations 4) Hybrid systems - the best of both worlds 5) Evaluating your recommendation system 6) Resources & existing libraries 5
6. What this Talk is Not • Everything there is to know about recommendation systems. • Bleeding edge machine learning • How to use a specific library 6
7. What is a recommendation system? 7
8. A program that predicts a user’s preferences using information about the user, other users, and the items in your system. 8
9. LinkedIn 9
10. Netflix 10
11. Spotify 11
12. Amazon 12
13. How do I build recommendations? 13
14. Two Main Categories of Algorithm 1. Collaborative Filtering (CF) 2. Content Based - Classification 14
15. Collaborative Filtering Fill in missing user preferences using similar users or items 15
16. 1. Memory Based - Uses similarity between users or items. Dataset usually kept in memory 2. Model Based - Model generated to “explain” observed ratings Two Types of CF 16
17. (User x Item) Matrix + Similarity Function = Top-K most similar users User Based CF 17
18. Video 1 Video 2 Video 3 Video 4 Video 5 User 1 User 2 User 3 User 4 User 5 0 1 0 5 0 1 2 1 0 5 2 5 0 0 2 5 4 4 1 1 2 4 ? ? 2 Collaborative Filtering * 0 denotes not rated 18
19. Similarity Functions • Pearson Correlation Coefficient • Cosine Similarity 19
20. Pearson Correlation Coefficient 20
21. Calculating PCC 21
22. Calculating PCC 22
23. Calculating PCC 23
24. Calculating PCC 24
25. Calculating PCC 25
26. Calculating PCC 26
28. Using similarity to recommend items 28
29. Video 1 Video 2 Video 3 Video 4 Video 5 User 1 User 2 User 3 User 4 User 5 0 1 0 5 0 1 2 1 0 5 2 5 0 0 2 5 4 4 1 1 2 4 ? ? 2 Collaborative Filtering * 0 denotes not rated 29
31. • Cold Start • Data Sparsity • Resource expensive Problems With CF 31
32. Doesn’t the video content matter for recommendations? 32
33. Content Based Recommendations Classify items based on features of the item. Pick other items from same class to recommend. 33
34. Content Based Algorithms • K-means clustering • Random Forrest • Support Vector Machines • ... • Insert your favorite ML algorithm 34
35. Content Based Algorithms Type of content Duration Maturity Rating Video 1 Video 2 Video 3 Video 4 Video 5 comedy 60 G action 120 G comedy 34 PG-13 romantic 15 R sports 120 G 35
36. K-means Clustering Group items into K clusters. Assign new item to a cluster and pick items from that cluster 36
37. K-means Clustering 37
38. • Unsupervised Learning is hard • Training data limited or expensive • Doesn’t take user into account • Limited by features of content Problems With Content Based Recommendations 38
39. Hybrid Recommendations Combine collaborative filtering with content based algorithm to achieve greater results 39
40. Hybrid Recommendations Content Based Recommender CF Based Recommender Combiner Reco Input Input 40
41. Hybrid Recommendations 41
42. Hybrid Recommendations Input CF Recommender Content Recommender Reco 42
43. Hybrid Recommendations CF Recommender Content Recommender Input Reco 43
44. Evaluating Recommendation Quality • Precision vs. Recall • Clicks • Click through rate • Direct user feedback 44
45. Precision vs. Recall 45
46. Precision vs. Recall 46
47. Summary of What We’ve Learned • Collaborative Filtering using similar users • Content clustering using k-means • Combining 2 algorithms to boost quality • How to evaluate your recommender 47
48. Don’t Reinvent the Wheel • Apache Mahout • JRuby mahout gem • SciRuby • Recommenderlab for R 48
49. Resources & Further Reading • Recommender Systems: An Introduction • Linden, Greg, Brent Smith, and Jeremy York. "Amazon. com recommendations: Item-to-item collaborative filtering." • Resnick, Paul, et al. "GroupLens: an open architecture for collaborative filtering of netnews." • ACM RecSys Conference Proceedings 49
50. We’re Hiring http://bit.ly/str-engineering 50
51. Thanks! Twitter: @rweald Email: ryan@sharethrough.com 51