Deep Learning for Recommender Systems
43 likes22,693 views
The document discusses the use of deep learning for recommender systems, emphasizing its potential to enhance personalization in recommendations, which significantly impacts customer satisfaction and revenue. It explores traditional and alternative recommendation setups, including various models and approaches such as matrix factorization and deep learning techniques. Key takeaways include the importance of contextual data and diverse modeling strategies to improve recommendation accuracy.
![Wide + Deep models
●
●
[Cheng et. al., 2016]](https://image.slidesharecdn.com/s81011-justinbasilicoandyvesraimond-180329160641/85/Deep-Learning-for-Recommender-Systems-23-320.jpg)
Deep Learning for Recommender Systems
- 1. Deep Learning for Recommender Systems Justin Basilico & Yves Raimond March 28, 2018 GPU Technology Conference @JustinBasilico @moustaki
- 2. The value of recommendations ● A few seconds to find something great to watch… ● Can only show a few titles ● Enjoyment directly impacts customer satisfaction ● Generates over $1B per year of Netflix revenue ● How? Personalize everything
- 3. Deep learning for recommendations: a first try
- 4. 0 1 0 1 0 0 0 1 1 0 1 0 0 1 1 0 1 0 0 0 0 0 0 0 1 UsersItems Traditional Recommendation Setup
- 5. U≈R V A Matrix Factorization view
- 6. U A Feed-Forward Network view V
- 7. U A (deeper) feed-forward view V Mean squared loss?
- 8. A quick & dirty experiment ● ○ ○ ● ○ ■ ■ ○ ■ ■ ■ ■ ■ ●
- 13. Conclusion? ● ●
- 14. Breaking the ‘traditional’ recsys setup ● ● ●
- 15. Alternative data
- 23. Wide + Deep models ● ● [Cheng et. al., 2016]
- 27. Contextual sequence data 2017-12-10 15:40:22 2017-12-23 19:32:10 2017-12-24 12:05:53 2017-12-27 22:40:22 2017-12-29 19:39:36 2017-12-30 20:42:13 Context ActionSequence per user ? Time
- 32. Conclusion
- 35. Thank you. @JustinBasilico @moustaki Justin Basilico & Yves Raimond Yes, we’re hiring...