Upgrade to Pro — share decks privately, control downloads, hide ads and more …

RecSysTV 2016 - Time Series Effects For TV Recommendations

05ee7b9a450069f210aac00cd5edd630?s=47 Diana Hu
September 15, 2016

RecSysTV 2016 - Time Series Effects For TV Recommendations

Recommendations for the television platform behave quite differently than the ones for video on demand platforms. A key difference is the dependency on television schedule and shows’ seasonality. In this talk, we will explore the time series effects that can be observed in the shows cyclicality, and more interestingly the effects of this cyclicality on users’ behavior. We’ll also go over some approaches to incorporate the time component onto different kinds of recommendations at Verizon IPTV

05ee7b9a450069f210aac00cd5edd630?s=128

Diana Hu

September 15, 2016
Tweet

Transcript

  1. TIME SERIES EFFECTS FOR TV RECOMMENDATIONS Diana Hu Verizon Labs

    RecSysTV, September 2016
  2. HELLO! ◦  Currently @ Verizon Labs ◦  Formerly @ Intel

    Labs ◦  Large Scale Machine Learning & Computer Vision ◦  Scala & Spark since 2014 You can find me at: @sdianahu
  3. DATA @ IPTV VERIZON ◦ Millions of subscribers ◦ Live TV playbacks

    ◦ DVR recordings ◦ DVR playbacks ◦ Time sensitive content by TV Schedule ◦ Hundreds of channels: Long tail
  4. TV EXPERIENCE

  5. SOME HISTORY first second http://www.brucesallan.com/2012/10/13/evolution-technology-television-back-day/ http://avdesigns.com/blog/design-your-own-at-home-sports-bar-with-a-multiscreen-tv-system/

  6. CREATURES OF HABIT

  7. CYCLICAL PATTERNS ◦ Prime time ◦ Weekend binge ◦ Sunday night football ◦ Basketball

    season ◦ Effect of Sitcoms ◦ Cartoons ◦ News
  8. TIME OF DAY VOLUME

  9. Time Segment Day Segment 6 MONTH TIME SERIES

  10. GENRE EFFECTS

  11. MAKING SENSE OF TIME Besides pretty visualizations…

  12. NAÏVE APPROACH

  13. FEATURE ENGINEERING ◦ Day parting ◦ Weekday parting ◦ Volatility spikes ◦ Intraday volatility

    ◦ Rank across time segments for: □ Channels □ Genres □ Programs
  14. UNLOCKING PREDICTIONS

  15. TIME AS A CONTEXT Enhancing recommendations

  16. SOME APPROACHES

  17. USE CASES ◦ Predicting viewership ◦ Personalization ◦ Re-Ranking ◦ Adapting to TV content

    “shelf life” ◦ Seasonality ◦ Trends
  18. ACKNOWLEDGEMENTS ◦ Luis M. Sanchez ◦ Humberto Corona

  19. THANKS! Any questions? You can find me at: @sdianahu diana.hu@verizon.com

    Also, we are hiring!