Story of the algorithms behind Deezer Flow

21
Story of the algorithms behind Deezer Flow RecSysFr, Paris, 2016 March 23th B. Mathieu, Data Architect T. Bouabca, Data Scientist

Transcript of Story of the algorithms behind Deezer Flow

Page 1: Story of the algorithms behind Deezer Flow

Story of the algorithms behind Deezer Flow

RecSysFr, Paris, 2016 March 23th

B. Mathieu, Data ArchitectT. Bouabca, Data Scientist

Page 2: Story of the algorithms behind Deezer Flow

/01

/02

/03

/04

/05

Context

Initial system

Content tagging system

Live adaptive algorithms

Conclusion

Story of the algorithms behindDeezer Flow

Story of the algorithms behind Deezer Flow

Page 3: Story of the algorithms behind Deezer Flow

Context

/01

Story of the algorithms behind Deezer Flow

Page 4: Story of the algorithms behind Deezer Flow

Deezer overview

/01 Context

Story of the algorithms behind Deezer Flow

● Music streaming service

● 6M paying users

● 40M tracks

● 180+ countries

● Up to 200+ tracks / user / day

Page 5: Story of the algorithms behind Deezer Flow

Story of the algorithms behind Deezer Flow

Adapt tracklist to● Music tastes● Localization● Activity● Mood● Time & day● Discovery preferences

Interesting debate

Should we ask questions to the user or let data science do the magic?

Deezer Flow: Initial pitchThe magic play button

Context/01

Page 6: Story of the algorithms behind Deezer Flow

Initial system

/02

Story of the algorithms behind Deezer Flow

Page 7: Story of the algorithms behind Deezer Flow

/02 Initial system

Story of the algorithms behind Deezer Flow

Available data:

● User likes (artists, albums, tracks)

● User streams logs● Album recommendation

algorithm (collaborative filtering)

Initial System (2014)

Strategy:

● Tracklist computed offline● Tracks from library / listening

habits● Tracks from recommended

albums

Page 8: Story of the algorithms behind Deezer Flow

/02 Initial system

Story of the algorithms behind Deezer Flow

Cold start problem: addressing new users

1. New users are asked to select some musical genres, and some artists

2. Build tracklist based on liked artists & similar artists

3. Fallback to top tracks in country

Page 9: Story of the algorithms behind Deezer Flow

/02 Initial system

Story of the algorithms behind Deezer Flow

● Tracklist only fits user’s tastes

● Tracklist do not fit user’s mood or user’s activity or time ...

To reach this goal:

● Immediately take into account user’s last interactions

● Refresh tracklist more often

● Insights into the content of a track

Need a more content-based approach

First Flow limitations

Page 10: Story of the algorithms behind Deezer Flow

Content tagging system

/03

Story of the algorithms behind Deezer Flow

Page 11: Story of the algorithms behind Deezer Flow

/03 Content tagging system

Story of the algorithms behind Deezer Flow

Building a content tagging system

Page 12: Story of the algorithms behind Deezer Flow

/03

Story of the algorithms behind Deezer Flow

● Heterogenous sources

● Millions of songs, artists, playlists or albums to tag everyday

Quality assessment:

● Monitoring every sources

● Benchmarking ● Studying new metrics

How to consolidate such data?

Content tagging system

Page 13: Story of the algorithms behind Deezer Flow

/03 Content tagging system

Story of the algorithms behind Deezer Flow

Architecture overview

Content data:- Tags- Popularity

User data:- Taste model- Hot tracks- Behaviors

Build tracklist

- Data cache- User action history

- Update user models- Consolidate tags data- Build indexes

actions logs

Page 14: Story of the algorithms behind Deezer Flow

Live adaptive algorithms

/04

Story of the algorithms behind Deezer Flow

Page 15: Story of the algorithms behind Deezer Flow

The live Flow (2015)

● Generated user profile● User history analyzed offline● Recently played tracks● Recent actions

● Querying tracks from ElasticSearch index

/04 Live adaptive algorithms

Story of the algorithms behind Deezer Flow

Page 16: Story of the algorithms behind Deezer Flow

Story of the algorithms behind Deezer Flow

Flat tag profiles can lead to mistakes

● Tag clustering

● Querying ES with different tag queries

● Serving tracks according to cluster proportion

/04

We can be more precise!

Live adaptive algorithms

Page 17: Story of the algorithms behind Deezer Flow

Different metrics to follow:

● Listening time

● Satisfaction

● User interaction (skipped / liked)

● Reconnection to Flow

Live evaluation - AB Testing

/04 Live adaptive algorithms

Story of the algorithms behind Deezer Flow

Page 18: Story of the algorithms behind Deezer Flow

Conclusion

/05

Story of the algorithms behind Deezer Flow

Page 19: Story of the algorithms behind Deezer Flow

Story of the algorithms behind Deezer Flow

What‘s next ?

● Fitting to user’s mood

● Increased performance on first days

Where are we now?

● Collaborative filtering combined with Content-Based approach (coming soon)

● More adaptation to the context

Conclusion/05

Page 20: Story of the algorithms behind Deezer Flow

We are hiring!

Story of the algorithms behind Deezer Flow

● Data scientist

● Data architect

● Search scientist

https://www.deezer.com/jobs

Conclusion/05

Page 21: Story of the algorithms behind Deezer Flow

21

Thanks for your attention

Questions?