Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation...
Transcript of Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation...
![Page 1: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/1.jpg)
Using Navigation to Improve Recommendations in Real-Time
Chao-Yuan Wu1, Chris Alvino2, Alex Smola3, Justin Basilico2
1 2 3
![Page 2: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/2.jpg)
What contents to show?
![Page 3: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/3.jpg)
Traditional recommender systems
History data Future behavior
![Page 4: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/4.jpg)
Watching alone, with friends, or with children?
?
?
![Page 5: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/5.jpg)
?
?
Who is watching? (shared accounts)
![Page 6: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/6.jpg)
May depend on your mood, how much time you have, etc.
?
?
![Page 7: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/7.jpg)
1. User intention depends on unpredictable factors2. User intention can vary significantly between sessions
Challenges
??
![Page 8: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/8.jpg)
1. Use context informationa. Time of day, day or week, device etc.
2. Present a mixture
Current solutions
![Page 9: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/9.jpg)
1. Use context informationa. Time of day, day or week, device etc.
2. Present a mixture
Current solutions
Can we do better?
![Page 10: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/10.jpg)
Skip
Navigation gives valuable information about user intent
Scroll
![Page 11: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/11.jpg)
Observenavigationsignals
Skip
Scroll
Skip
![Page 12: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/12.jpg)
NavigationsignalUpdate unseen
rows in real-time
Scroll
Skip
![Page 13: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/13.jpg)
Online adaptation framework
Offline System Page
Navigation
online/browser
![Page 14: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/14.jpg)
Completely general - whenever contents don’t fit on single display
![Page 15: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/15.jpg)
1. Contents organized in rows2. Horizontal or vertical scrolls
Focus on a case based on Netflix PS3 UI
![Page 16: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/16.jpg)
1. Contents organized in rows2. Horizontal or vertical scrolls 3. Scrolls as navigation signals4. Consider reordering rows, while videos in a row are
fixed
Focus on a case based on Netflix PS3 UI
![Page 17: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/17.jpg)
Model & Algorithm
![Page 18: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/18.jpg)
Comedies
Documentaries
Action Movies
Sci-Fi
Videos organized in rows
![Page 19: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/19.jpg)
Comedies
Documentaries
Action Movies
Sci-Fi
Latent “interest” variable
![Page 20: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/20.jpg)
Only scroll or play from rows that user is interested in
![Page 21: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/21.jpg)
Comedies
Romantic comedies
Action Movies
Sci-Fi
Initial page
![Page 22: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/22.jpg)
Comedies
Romantic comedies
Action Movies
Sci-Fi
User interacts with the page
Skip
![Page 23: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/23.jpg)
Comedies
Romantic comedies
Action Movies
Sci-Fi
Update intent estimation
Skip
![Page 24: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/24.jpg)
Comedies
Romantic comedies
Action Movies
Sci-Fi
Rearrange page
Skip
![Page 25: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/25.jpg)
Model
row
video
![Page 26: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/26.jpg)
Model
Scroll
Play
Interest
![Page 27: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/27.jpg)
Online adaptation
Scroll
Play
Interest
1. Observe2. Update
session-specific parameters
3. Update marginal probability
![Page 28: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/28.jpg)
Offline training to estimate long-term preference by EM Algorithm
1. E-step: estimate “interest” .
2. M-step: optimize all other variables
![Page 29: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/29.jpg)
Choice of the model
1. Independent of the function classa. Inner product, FM, deep networks, etc. b. We use submodular functions
(see e.g. Ahmed et al. WSDM ‘12) .
2. Tightly coupled with the UI design
![Page 30: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/30.jpg)
Roundtrips to a server add latency
updateupdate
![Page 31: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/31.jpg)
Efficient in-browser updates with prefetching
updateupdate
![Page 32: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/32.jpg)
Experiments
![Page 33: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/33.jpg)
● Netflix PlayStation 3 sessions. ● Training: April-May 2015 (294k sessions)● Testing: June 2015 (59k sessions)● 40 rows per page● 75 videos per row (max)
Dataset
![Page 34: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/34.jpg)
Conditional play probability increases as the user delves into the list
![Page 35: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/35.jpg)
● Fix 10 rows, and update rows below● Row considered positive if any video in the row is played● Metrics:
○ Mean reciprocal rank (MRR)○ Precision @ 5
● Baseline: Factorization Machine over user and row○ libFM [S. Rendle 2012] implementation
Evaluating online adaptation
![Page 36: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/36.jpg)
Online adaptation improves recommendations
![Page 37: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/37.jpg)
Online adaptation helps with cold-start
![Page 38: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/38.jpg)
Model fatigue effects and repeated plays to get accurate predictions
![Page 39: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/39.jpg)
Model fatigue effects and repeated plays to get accurate predictions
![Page 40: Using Navigation to Improve Recommendations in Real-Timecywu/RecSys2016_slides.pdfUsing Navigation to Improve Recommendations in Real-Time Chao-Yuan Wu1, Chris Alvino2, Alex Smola3,](https://reader034.fdocuments.us/reader034/viewer/2022042104/5e81ad0f09fccc2f663474d2/html5/thumbnails/40.jpg)
1. Using navigation toa. improve recommendations in real-timeb. help with cold-start
2. Efficient in-browser update by pre-fetching3. Model fatigue effects and repeated plays to get
accurate play predictions4. General framework
a. Can be applied to many user interfaces
Summary