SlideShare a Scribd company logo
1 of 26
Download to read offline
Recommendation
Challenges in Web Media
        Settings

     Ronny Lempel
 Yahoo! Labs, Haifa, Israel
Recommender Systems
 • Pioneered in the mid/late 90s by Amazon




 • Today applied “everywhere”
    • Shopping sites
    • Content sites (news, sports, gossip, …)
    • Multimedia streaming services (videos, music)
    • Social networks
 • Easily merit a dedicated academic course

                            -1-           Bangalore/MumbaiConfidential
                                                     Yahoo! 2013
Recommendation in Social Networks




                      -2-       Bangalore/MumbaiConfidential
                                           Yahoo! 2013
Recommender Systems – Example of Effectiveness
  • 1988: Random House releases
    “Touching the Void”, a book by a
    mountain climber detailing a harrowing
    account of near death in the Andes
     – It got good reviews but modest commercial
       success
  • 1999: “Into Thin Air”, another mountain-climbing tragedy
    book, becomes a best-seller
  • By virtue of Amazon’s recommender system, “Touching
    the Void” started to sell again, prompting Random House
    to rush out a new edition
     – A revised paperback edition spent 14 weeks on the New York
       Times bestseller list
                               From “The Long Tail”, by Chris Anderson

                                 -3-               Bangalore/MumbaiConfidential
                                                              Yahoo! 2013
The Netflix Challenge




Slides 4-6 courtesy of
Yehuda Koren, member
of Challenge winners
“Bellkor’s Pragmatic
Chaos”




                         -4-   Bangalore/MumbaiConfidential
                                          Yahoo! 2013
“We’re quite curious, really. To the tune of
one million dollars.” – Netflix Prize rules
  • Goal was to improve on Netflix’ existing movie
    recommendation technology
  • The open-to-the-public contest began October 2, 2006;
    winners announced September 2009
  • Prize
     – Based on reduction in root mean squared error (RMSE) on test data
     – $1 million grand prize for 10% improvement on Cinematch result
     – $50K 2007 progress prize for 8.43% improvement
     – $50K 2008 progress prize for 9.44% improvement
  • Netflix gets full rights to use IP developed by the winners
     – Example of Crowdsourcing – Netflix basically got over 100
       researcher years (and good publicity) for $1.1M


                                  -5-              Bangalore/MumbaiConfidential
                                                              Yahoo! 2013
Netflix Movie Ratings Data
                               Training data                     Test data
• Training data           user     movie       score     user      movie
   – 100 million           1         21          1         1          62              ?
      ratings
                           1        213          5         1          96              ?
   – 480,000 users
                           2        345          4         2          7               ?
   – 17,770 movies
   – 6 years of data:      2        123          4         2          3               ?
      2000-2005            2        768          3         3          47              ?
• Test data                3         76          5         3          15              ?
   – Last few ratings      4         45          4         4          41              ?
      of each user (2.8    5        568          1         4          28              ?
      million)             5        342          2         5          93              ?
• Dates of ratings are     5        234          2         5          74              ?
  given
                           6         76          5         6          69              ?
                           6         56          4         6          83              ?



                                    -6-                Bangalore/MumbaiConfidential
                                                                  Yahoo! 2013
Recommender Systems – Mathematical Abstraction
   • Consider a matrix R of users and the items they’ve
     consumed
      – Users correspond to the rows of R, products to its columns, with
        ri,j=1 whenever person i consumed item j
      – In other cases, ri,j might be the rating given by person i on item j
   • The matrix R is typically very sparse
                                                                            Items
      – …and often very large
   • Real-life task: top-k recommendation




                                                                 users
      – From among the items that weren’t               R=
        consumed by each user, predict which
        ones the user would most enjoy
   • Related task on ratings data: matrix
     completion                                                          |U| x |I|
      – Predict users’ ratings for items they have
        yet to rate, i.e. “complete” missing values
                                   -7-                Bangalore/MumbaiConfidential
                                                                 Yahoo! 2013
Types of Recommender Systems
 At a high level, two main techniques:
 • Content-based recommendation: characterizes the
    affinity of users to certain features (content, metadata)
    of their preferred items
    – Lots of classification technology under the hood
 • Collaborative Filtering: exploits similar consumption
   and preference patterns between users
    – See next slides
 • Many state of the art systems combine both techniques




                                   -8-              Bangalore/MumbaiConfidential
                                                               Yahoo! 2013
Collaborative Filtering – Neighborhood Models

   • Compute the similarity of items [users] to each other
      – Items are considered similar when users tend to rate them
        similarly or to co-consume them
      – Users are considered similar when they tend to co-consume
        items or rate items similarly
   • Recommend to a user:
      – Items similar to items he/she has already consumed [rated
        highly]
      – Items consumed [rated highly] by similar users
   • Key questions:
      – How exactly to define pair-wise similarities?
      – How to combine them into quality recommendations?



                                  -9-               Bangalore/MumbaiConfidential
                                                               Yahoo! 2013
Collaborative Filtering – Matrix Factorization

  • Latent factor models (LFM):
     – Maps both users and items to some f-dimensional space Rf, i.e.
       produce f-dimensional vectors vu and wi for each user and items
     – Define rating estimates as inner products: qij = <vi,wj>
     – Main problem: finding a mapping of users and items to the latent
       factor space that produces “good” estimates
     – Closely related to dimensionality reduction techniques of the
       ratings matrix R (e.g. Singular Value Decomposition)
                   Items            V
                                                      W
         users




    R=                       ≈


                 |U| x |I|       |U| x f            f x |I|
                                           - 10 -             Bangalore/MumbaiConfidential
                                                                         Yahoo! 2013
Web Media Sites




                  - 11 -   Bangalore/MumbaiConfidential
                                      Yahoo! 2013
Challenge: Cold Start Problems
  • Good recommendations require observed data on the user
    being recommended to [the items being recommended]
     – What did the user consume/enjoy before?
     – Which users consumed/enjoyed this item before?
  • User cold start: what happens when a new user arrives to a
    system?
     – How can the system make a good “first impression”?
  • Item cold start: how do we recommend newly arrived items
    with little historic consumption?
  • In certain settings, items are
    ephemeral – a significant portion of
    their lifetime is spent in cold-start state
     – E.g. news recommendation


                                 - 12 -           Bangalore/MumbaiConfidential
                                                             Yahoo! 2013
Low False-Positive Costs
  False positive: recommending an irrelevant item
  • Consequence, in media sites: a bit of lost time
     – As opposed to lots of lost time or money in other settings
  • Opportunity: better address cold-start issues
  • Item cold-start: show new item to select group of users
    whose feedback should help in modeling it to everyone
     – Note the very short item life times in news cycles
  • User cold-start: more aggressive exploration
     – Vs. playing it safe and perpetuating popular items
  • Search: injecting randomization into the ranking of search
    results (Pandey et al., VLDB 2005)



                                  - 13 -           Bangalore/MumbaiConfidential
                                                              Yahoo! 2013
Challenge: Inferring Negative Feedback
  • In many recommendation settings we only know which
    items users have consumed, not whether they liked them
     – I.e. no explicit ratings data
  • What can we infer about satisfaction of consumed items
    from observing other interactions with the content?
     – Web pages: what happens after the initial click?
     – Short online videos: what happens after pressing “play”?
     – TV programs: zapping patterns
  • What can we infer about items the user did not consume?
  • Was the user even aware of the items he/she did not
    consume?
     – What items did the recommender system expose the user to?



                                       - 14 -      Bangalore/MumbaiConfidential
                                                              Yahoo! 2013
Presentation Bias’ Effect on Media Consumption
  • Pop Culture: items’ longevity creates familiarity




  • Media sites: items are ephemeral, and users are mostly
    unaware of items the site did not expose them to
  • Presentation bias obscures users’ true taste – they
    essentially select the best of the little that was shown
  • Must correctly account for presentation bias when
    modeling: seen and not selected ≠ not seen and not
    selected
  • Search: negative interpretation of “skipped” search results
    (Joachims, KDD’2002)
                              - 15 -         Bangalore/MumbaiConfidential
                                                        Yahoo! 2013
Layouts of Recommendation Modules




  • Interpreting interactions in vertical layouts is “easy” using
    the “skips” paradigm
  • What about 2D, tabbed, horizontal layouts?

                               - 16 -         Bangalore/MumbaiConfidential
                                                         Yahoo! 2013
Layouts of Recommendation Modules




                              • What about multiple
                                presentation formats?




                     - 17 -         Bangalore/MumbaiConfidential
                                               Yahoo! 2013
Personalized




                                            Popular




Contextual




             - 18 -   Bangalore/MumbaiConfidential
                                 Yahoo! 2013
Contextualized, Personalization, Popular
   • Web media sites often display links to additional stories
     on each article page
      – Matching the article’s context, matching the user, consumed by
        the user’s friends, popular
   • When creating a unified list for a given a user reading a
     specific page, what should be the relative importance of
     matching the additional stories to the page vs. matching
     to the user?
   • Ignoring story context might create offending
     recommendations
   • Related direction: Tensor Factorization, Karatzoglou et.
     al, RecSys’2010




                                  - 19 -           Bangalore/MumbaiConfidential
                                                              Yahoo! 2013
Challenge: Incremental Collaborative Filtering
  •   In a live system, we often cannot afford to recompute
      recommendations regularly over the entire history
  •   Problem: neither neighborhood models nor matrix
      factorization models easily lend themselves to faithful
      incremental processing

       User-Item      User-Item      User-Item              Mi = CF-ALG(ti)
      Interactions   Interactions   Interactions

           t1             t2             t3
                                                            ∀f, f { M1, M2 } ≠ CF_ALG(t1∪t2)
                                                   …

                                                       T
  •   Is there a model aggregation function f(Mprev, Mcurr) that is
      “good enough”?


                                                   - 20 -             Bangalore/MumbaiConfidential
                                                                                 Yahoo! 2013
Challenge: Repeated Recommendations
  • One typically doesn’t buy the same book twice, nor do
    people typically read the same news story twice
  • But people listen to the songs they like over and over
    again, and watch movies they like multiple times as well
  • When and how frequently is it ok to recommend an item
    that was already consumed?
  • On the other hand, when should we stop showing a
    recommendation if the user doesn’t act upon it?
  • Implication: a recommendation system may not only need
    to track aggregated consumption to-date,
     – It may need to track consumption timelines
     – It may need to track recommendation history




                                - 21 -           Bangalore/MumbaiConfidential
                                                            Yahoo! 2013
Challenge: Recommending Sets & Sequences of
Items
  • In some domains, users consume multiple items in rapid
    succession (e.g. music playlists)
     – Recent works: WWW’2012 (Aizenberg et al., sets) and KDD’2012
       (Chen et al., sequences)
  • From Independent utility of recommendations to set or
    sequence utility, predicting items that “go well together”
     – Sometimes need to respect constraints
  • Tiling recommendations: in TV Watchlist generation, the
    broadcast schedules further complicates matters due to
    program overlaps
  • Perhaps a new domain of constrained recommendations?
  • Search: result set attributes (e.g. diversity) in Search
    (Agrawal et al., WSDM’2009)
  • Netflix tutorial at RecSys’2012: diversity is key @Netflix

                                - 22 -         Bangalore/MumbaiConfidential
                                                          Yahoo! 2013
Social Networks and Recommendation
Computation
  • Some are hailing social networks as a
    silver bullet for recommender systems
     – Tell me who your friends are and we’ll tell
       you what you like
  • Is it really the case that we like the
    same media as our friends?
  • Affinity trumps friendship!
     – There are people out there who are “more
       like us” than our limited set of friends
     – Once affinity is considered, the marginal
       value of social connections is often
       negligible
  • Not to be confused with non-friendship social networks,
    where connections are affinity related (Epinions)


                                  - 23 -             Bangalore/MumbaiConfidential
                                                                Yahoo! 2013
                                                                 RecSys 202
Social Networks and Recommendation
Consumption
  • Previous slide nonewithstanding, “social” is a great
    motivator for consuming recommendations
     – People like you rate “Lincoln” very highly     vs.
     – Your friends Alice and Bob saw “Lincoln” last night and loved it
  • Explaining recommendations for motivating and increasing
    consumption is an emerging practice
  • Some commercial systems completely separate their
    explanation generation from their recommendation generation
     – So Alice and Bob may not be why the system recommended
       “Lincoln” to you, but they will be leveraged to get you to watch it
  • Privacy in the face of joint consumption of a personalized
    experience?




                                   - 24 -            Bangalore/MumbaiConfidential
                                                                Yahoo! 2013
                                                                 RecSys 202
Questions, Comments?




                Thank you!

        rlempel (at) yahoo-inc dot com




                       - 25 -            Yahoo! Confidential

More Related Content

Viewers also liked

Meta Analysis of Medical Device Data Applications for Designing Studies and R...
Meta Analysis of Medical Device Data Applications for Designing Studies and R...Meta Analysis of Medical Device Data Applications for Designing Studies and R...
Meta Analysis of Medical Device Data Applications for Designing Studies and R...NAMSA
 
Bowen & Neill (2013) Adventure Therapy Meta-Analysis Presentation
Bowen & Neill (2013) Adventure Therapy Meta-Analysis PresentationBowen & Neill (2013) Adventure Therapy Meta-Analysis Presentation
Bowen & Neill (2013) Adventure Therapy Meta-Analysis PresentationDaniel Bowen
 
Social media-marketing-the closet-fabian-espinosa
Social media-marketing-the closet-fabian-espinosaSocial media-marketing-the closet-fabian-espinosa
Social media-marketing-the closet-fabian-espinosaFabian Espinosa
 
Network meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistencyNetwork meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistencycheweb1
 
Social+search+ad,社群與SEO的交互關係
Social+search+ad,社群與SEO的交互關係Social+search+ad,社群與SEO的交互關係
Social+search+ad,社群與SEO的交互關係煜庭 邱
 
Why repeated meta-analyses can show very different results?
Why repeated meta-analyses can show very different results?Why repeated meta-analyses can show very different results?
Why repeated meta-analyses can show very different results?Reijo Laatikainen
 
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEM
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEMIMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEM
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEMhowell00
 
Flickr簡介+部落客必學招式
Flickr簡介+部落客必學招式Flickr簡介+部落客必學招式
Flickr簡介+部落客必學招式Tien-Chih (Tenz) Shih
 
Coding Dojo: Baby Steps (2014)
Coding Dojo: Baby Steps (2014)Coding Dojo: Baby Steps (2014)
Coding Dojo: Baby Steps (2014)Peter Kofler
 
Portada Online Video Forum 2015
Portada Online Video Forum 2015Portada Online Video Forum 2015
Portada Online Video Forum 2015Portada
 
Nexenta at VMworld Hands-on Lab
Nexenta at VMworld Hands-on LabNexenta at VMworld Hands-on Lab
Nexenta at VMworld Hands-on LabNexenta Systems
 
Stefan Decker Keynote at CSHALS
Stefan Decker Keynote at CSHALSStefan Decker Keynote at CSHALS
Stefan Decker Keynote at CSHALSStefan Decker
 
Vik Bhatti (Beamly) - Service Discovery for DevOps
Vik Bhatti (Beamly) - Service Discovery for DevOpsVik Bhatti (Beamly) - Service Discovery for DevOps
Vik Bhatti (Beamly) - Service Discovery for DevOpsOutlyer
 
Bravo motor company overview deck january 2015
Bravo motor company overview deck january 2015Bravo motor company overview deck january 2015
Bravo motor company overview deck january 2015Grupo ArqBravo
 
Sass, Compass and the new tools - Open Web Camp IV
Sass, Compass and the new tools - Open Web Camp IVSass, Compass and the new tools - Open Web Camp IV
Sass, Compass and the new tools - Open Web Camp IVDirk Ginader
 
Yahoo Connected TV Developer Pulse Event
Yahoo Connected TV Developer Pulse EventYahoo Connected TV Developer Pulse Event
Yahoo Connected TV Developer Pulse EventYahooConnectedTV
 
LUXr (Lean + UX)*Agile=awesome
LUXr (Lean + UX)*Agile=awesomeLUXr (Lean + UX)*Agile=awesome
LUXr (Lean + UX)*Agile=awesomeLUXr
 
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016Daniel Caridi
 

Viewers also liked (20)

Meta Analysis of Medical Device Data Applications for Designing Studies and R...
Meta Analysis of Medical Device Data Applications for Designing Studies and R...Meta Analysis of Medical Device Data Applications for Designing Studies and R...
Meta Analysis of Medical Device Data Applications for Designing Studies and R...
 
Perspectivas de la comunicación 2016
Perspectivas de la comunicación 2016Perspectivas de la comunicación 2016
Perspectivas de la comunicación 2016
 
Bowen & Neill (2013) Adventure Therapy Meta-Analysis Presentation
Bowen & Neill (2013) Adventure Therapy Meta-Analysis PresentationBowen & Neill (2013) Adventure Therapy Meta-Analysis Presentation
Bowen & Neill (2013) Adventure Therapy Meta-Analysis Presentation
 
Atac cerebral
Atac cerebralAtac cerebral
Atac cerebral
 
Social media-marketing-the closet-fabian-espinosa
Social media-marketing-the closet-fabian-espinosaSocial media-marketing-the closet-fabian-espinosa
Social media-marketing-the closet-fabian-espinosa
 
Network meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistencyNetwork meta-analysis & models for inconsistency
Network meta-analysis & models for inconsistency
 
Social+search+ad,社群與SEO的交互關係
Social+search+ad,社群與SEO的交互關係Social+search+ad,社群與SEO的交互關係
Social+search+ad,社群與SEO的交互關係
 
Why repeated meta-analyses can show very different results?
Why repeated meta-analyses can show very different results?Why repeated meta-analyses can show very different results?
Why repeated meta-analyses can show very different results?
 
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEM
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEMIMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEM
IMPORTANCE OF NURSING INFORMATICS IN THE PHILIPPINE HEALTH CARE DELIVERY SYSTEM
 
Flickr簡介+部落客必學招式
Flickr簡介+部落客必學招式Flickr簡介+部落客必學招式
Flickr簡介+部落客必學招式
 
Coding Dojo: Baby Steps (2014)
Coding Dojo: Baby Steps (2014)Coding Dojo: Baby Steps (2014)
Coding Dojo: Baby Steps (2014)
 
Portada Online Video Forum 2015
Portada Online Video Forum 2015Portada Online Video Forum 2015
Portada Online Video Forum 2015
 
Nexenta at VMworld Hands-on Lab
Nexenta at VMworld Hands-on LabNexenta at VMworld Hands-on Lab
Nexenta at VMworld Hands-on Lab
 
Stefan Decker Keynote at CSHALS
Stefan Decker Keynote at CSHALSStefan Decker Keynote at CSHALS
Stefan Decker Keynote at CSHALS
 
Vik Bhatti (Beamly) - Service Discovery for DevOps
Vik Bhatti (Beamly) - Service Discovery for DevOpsVik Bhatti (Beamly) - Service Discovery for DevOps
Vik Bhatti (Beamly) - Service Discovery for DevOps
 
Bravo motor company overview deck january 2015
Bravo motor company overview deck january 2015Bravo motor company overview deck january 2015
Bravo motor company overview deck january 2015
 
Sass, Compass and the new tools - Open Web Camp IV
Sass, Compass and the new tools - Open Web Camp IVSass, Compass and the new tools - Open Web Camp IV
Sass, Compass and the new tools - Open Web Camp IV
 
Yahoo Connected TV Developer Pulse Event
Yahoo Connected TV Developer Pulse EventYahoo Connected TV Developer Pulse Event
Yahoo Connected TV Developer Pulse Event
 
LUXr (Lean + UX)*Agile=awesome
LUXr (Lean + UX)*Agile=awesomeLUXr (Lean + UX)*Agile=awesome
LUXr (Lean + UX)*Agile=awesome
 
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016
eMarketer Webinar: Cross-Device Targeting—What to Watch for in 2016
 

Similar to Ronny lempelyahooindiabigthinkerapril2013

Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...
Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...
Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...Sc Huang
 
Recommender system introduction
Recommender system   introductionRecommender system   introduction
Recommender system introductionLiang Xiang
 
Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface晓愚 孟
 
Recommandation systems -
Recommandation systems - Recommandation systems -
Recommandation systems - Yousef Fadila
 
Usability evaluations (part 2)
Usability evaluations (part 2) Usability evaluations (part 2)
Usability evaluations (part 2) Andres Baravalle
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Ernesto Mislej
 
IntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdfIntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdfAlphaIssaghaDiallo
 
productionising-recommenders
productionising-recommendersproductionising-recommenders
productionising-recommendersLudovik Coba
 
Utilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerceUtilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerceLiangjie Hong
 
Chapter 02 collaborative recommendation
Chapter 02   collaborative recommendationChapter 02   collaborative recommendation
Chapter 02 collaborative recommendationAravindharamanan S
 
Chapter 02 collaborative recommendation
Chapter 02   collaborative recommendationChapter 02   collaborative recommendation
Chapter 02 collaborative recommendationAravindharamanan S
 
Matrix Factorization Techniques For Recommender Systems
Matrix Factorization Techniques For Recommender SystemsMatrix Factorization Techniques For Recommender Systems
Matrix Factorization Techniques For Recommender SystemsLei Guo
 
2.social recommedation
2.social recommedation2.social recommedation
2.social recommedationjilung hsieh
 
Product Recommendations Enhanced with Reviews
Product Recommendations Enhanced with ReviewsProduct Recommendations Enhanced with Reviews
Product Recommendations Enhanced with Reviewsmaranlar
 
recommendation system techunique and issue
recommendation system techunique and issuerecommendation system techunique and issue
recommendation system techunique and issueNutanBhor
 

Similar to Ronny lempelyahooindiabigthinkerapril2013 (20)

Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...
Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...
Random Walk by User Trust and Temporal Issues toward Sparsity Problem in Soci...
 
Recommender system introduction
Recommender system   introductionRecommender system   introduction
Recommender system introduction
 
Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface
 
Recommandation systems -
Recommandation systems - Recommandation systems -
Recommandation systems -
 
Usability evaluations (part 2)
Usability evaluations (part 2) Usability evaluations (part 2)
Usability evaluations (part 2)
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
IntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdfIntroductionRecommenderSystems_Petroni.pdf
IntroductionRecommenderSystems_Petroni.pdf
 
productionising-recommenders
productionising-recommendersproductionising-recommenders
productionising-recommenders
 
Don’t make me think!
Don’t make me think!Don’t make me think!
Don’t make me think!
 
Utilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerceUtilizing Marginal Net Utility for Recommendation in E-commerce
Utilizing Marginal Net Utility for Recommendation in E-commerce
 
Chapter 02 collaborative recommendation
Chapter 02   collaborative recommendationChapter 02   collaborative recommendation
Chapter 02 collaborative recommendation
 
Chapter 02 collaborative recommendation
Chapter 02   collaborative recommendationChapter 02   collaborative recommendation
Chapter 02 collaborative recommendation
 
Matrix Factorization Techniques For Recommender Systems
Matrix Factorization Techniques For Recommender SystemsMatrix Factorization Techniques For Recommender Systems
Matrix Factorization Techniques For Recommender Systems
 
Fashiondatasc
FashiondatascFashiondatasc
Fashiondatasc
 
2.social recommedation
2.social recommedation2.social recommedation
2.social recommedation
 
Product Recommendations Enhanced with Reviews
Product Recommendations Enhanced with ReviewsProduct Recommendations Enhanced with Reviews
Product Recommendations Enhanced with Reviews
 
Paper prototype evaluation
Paper prototype evaluationPaper prototype evaluation
Paper prototype evaluation
 
recommendation system techunique and issue
recommendation system techunique and issuerecommendation system techunique and issue
recommendation system techunique and issue
 

Recently uploaded

Proudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxProudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxthorishapillay1
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...Nguyen Thanh Tu Collection
 
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...JhezDiaz1
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxEPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxRaymartEstabillo3
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designMIPLM
 
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxMULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxAnupkumar Sharma
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxOH TEIK BIN
 
Quarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayQuarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayMakMakNepo
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTiammrhaywood
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfMr Bounab Samir
 
AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.arsicmarija21
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfSpandanaRallapalli
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxiammrhaywood
 

Recently uploaded (20)

Proudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptxProudly South Africa powerpoint Thorisha.pptx
Proudly South Africa powerpoint Thorisha.pptx
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
 
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
Model Call Girl in Bikash Puri Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Bikash Puri  Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Bikash Puri  Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Bikash Puri Delhi reach out to us at 🔝9953056974🔝
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxEPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-design
 
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptxMULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
MULTIDISCIPLINRY NATURE OF THE ENVIRONMENTAL STUDIES.pptx
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptx
 
Quarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayQuarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up Friday
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
 
9953330565 Low Rate Call Girls In Rohini Delhi NCR
9953330565 Low Rate Call Girls In Rohini  Delhi NCR9953330565 Low Rate Call Girls In Rohini  Delhi NCR
9953330565 Low Rate Call Girls In Rohini Delhi NCR
 
AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdf
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
 

Ronny lempelyahooindiabigthinkerapril2013

  • 1. Recommendation Challenges in Web Media Settings Ronny Lempel Yahoo! Labs, Haifa, Israel
  • 2. Recommender Systems • Pioneered in the mid/late 90s by Amazon • Today applied “everywhere” • Shopping sites • Content sites (news, sports, gossip, …) • Multimedia streaming services (videos, music) • Social networks • Easily merit a dedicated academic course -1- Bangalore/MumbaiConfidential Yahoo! 2013
  • 3. Recommendation in Social Networks -2- Bangalore/MumbaiConfidential Yahoo! 2013
  • 4. Recommender Systems – Example of Effectiveness • 1988: Random House releases “Touching the Void”, a book by a mountain climber detailing a harrowing account of near death in the Andes – It got good reviews but modest commercial success • 1999: “Into Thin Air”, another mountain-climbing tragedy book, becomes a best-seller • By virtue of Amazon’s recommender system, “Touching the Void” started to sell again, prompting Random House to rush out a new edition – A revised paperback edition spent 14 weeks on the New York Times bestseller list From “The Long Tail”, by Chris Anderson -3- Bangalore/MumbaiConfidential Yahoo! 2013
  • 5. The Netflix Challenge Slides 4-6 courtesy of Yehuda Koren, member of Challenge winners “Bellkor’s Pragmatic Chaos” -4- Bangalore/MumbaiConfidential Yahoo! 2013
  • 6. “We’re quite curious, really. To the tune of one million dollars.” – Netflix Prize rules • Goal was to improve on Netflix’ existing movie recommendation technology • The open-to-the-public contest began October 2, 2006; winners announced September 2009 • Prize – Based on reduction in root mean squared error (RMSE) on test data – $1 million grand prize for 10% improvement on Cinematch result – $50K 2007 progress prize for 8.43% improvement – $50K 2008 progress prize for 9.44% improvement • Netflix gets full rights to use IP developed by the winners – Example of Crowdsourcing – Netflix basically got over 100 researcher years (and good publicity) for $1.1M -5- Bangalore/MumbaiConfidential Yahoo! 2013
  • 7. Netflix Movie Ratings Data Training data Test data • Training data user movie score user movie – 100 million 1 21 1 1 62 ? ratings 1 213 5 1 96 ? – 480,000 users 2 345 4 2 7 ? – 17,770 movies – 6 years of data: 2 123 4 2 3 ? 2000-2005 2 768 3 3 47 ? • Test data 3 76 5 3 15 ? – Last few ratings 4 45 4 4 41 ? of each user (2.8 5 568 1 4 28 ? million) 5 342 2 5 93 ? • Dates of ratings are 5 234 2 5 74 ? given 6 76 5 6 69 ? 6 56 4 6 83 ? -6- Bangalore/MumbaiConfidential Yahoo! 2013
  • 8. Recommender Systems – Mathematical Abstraction • Consider a matrix R of users and the items they’ve consumed – Users correspond to the rows of R, products to its columns, with ri,j=1 whenever person i consumed item j – In other cases, ri,j might be the rating given by person i on item j • The matrix R is typically very sparse Items – …and often very large • Real-life task: top-k recommendation users – From among the items that weren’t R= consumed by each user, predict which ones the user would most enjoy • Related task on ratings data: matrix completion |U| x |I| – Predict users’ ratings for items they have yet to rate, i.e. “complete” missing values -7- Bangalore/MumbaiConfidential Yahoo! 2013
  • 9. Types of Recommender Systems At a high level, two main techniques: • Content-based recommendation: characterizes the affinity of users to certain features (content, metadata) of their preferred items – Lots of classification technology under the hood • Collaborative Filtering: exploits similar consumption and preference patterns between users – See next slides • Many state of the art systems combine both techniques -8- Bangalore/MumbaiConfidential Yahoo! 2013
  • 10. Collaborative Filtering – Neighborhood Models • Compute the similarity of items [users] to each other – Items are considered similar when users tend to rate them similarly or to co-consume them – Users are considered similar when they tend to co-consume items or rate items similarly • Recommend to a user: – Items similar to items he/she has already consumed [rated highly] – Items consumed [rated highly] by similar users • Key questions: – How exactly to define pair-wise similarities? – How to combine them into quality recommendations? -9- Bangalore/MumbaiConfidential Yahoo! 2013
  • 11. Collaborative Filtering – Matrix Factorization • Latent factor models (LFM): – Maps both users and items to some f-dimensional space Rf, i.e. produce f-dimensional vectors vu and wi for each user and items – Define rating estimates as inner products: qij = <vi,wj> – Main problem: finding a mapping of users and items to the latent factor space that produces “good” estimates – Closely related to dimensionality reduction techniques of the ratings matrix R (e.g. Singular Value Decomposition) Items V W users R= ≈ |U| x |I| |U| x f f x |I| - 10 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 12. Web Media Sites - 11 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 13. Challenge: Cold Start Problems • Good recommendations require observed data on the user being recommended to [the items being recommended] – What did the user consume/enjoy before? – Which users consumed/enjoyed this item before? • User cold start: what happens when a new user arrives to a system? – How can the system make a good “first impression”? • Item cold start: how do we recommend newly arrived items with little historic consumption? • In certain settings, items are ephemeral – a significant portion of their lifetime is spent in cold-start state – E.g. news recommendation - 12 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 14. Low False-Positive Costs False positive: recommending an irrelevant item • Consequence, in media sites: a bit of lost time – As opposed to lots of lost time or money in other settings • Opportunity: better address cold-start issues • Item cold-start: show new item to select group of users whose feedback should help in modeling it to everyone – Note the very short item life times in news cycles • User cold-start: more aggressive exploration – Vs. playing it safe and perpetuating popular items • Search: injecting randomization into the ranking of search results (Pandey et al., VLDB 2005) - 13 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 15. Challenge: Inferring Negative Feedback • In many recommendation settings we only know which items users have consumed, not whether they liked them – I.e. no explicit ratings data • What can we infer about satisfaction of consumed items from observing other interactions with the content? – Web pages: what happens after the initial click? – Short online videos: what happens after pressing “play”? – TV programs: zapping patterns • What can we infer about items the user did not consume? • Was the user even aware of the items he/she did not consume? – What items did the recommender system expose the user to? - 14 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 16. Presentation Bias’ Effect on Media Consumption • Pop Culture: items’ longevity creates familiarity • Media sites: items are ephemeral, and users are mostly unaware of items the site did not expose them to • Presentation bias obscures users’ true taste – they essentially select the best of the little that was shown • Must correctly account for presentation bias when modeling: seen and not selected ≠ not seen and not selected • Search: negative interpretation of “skipped” search results (Joachims, KDD’2002) - 15 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 17. Layouts of Recommendation Modules • Interpreting interactions in vertical layouts is “easy” using the “skips” paradigm • What about 2D, tabbed, horizontal layouts? - 16 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 18. Layouts of Recommendation Modules • What about multiple presentation formats? - 17 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 19. Personalized Popular Contextual - 18 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 20. Contextualized, Personalization, Popular • Web media sites often display links to additional stories on each article page – Matching the article’s context, matching the user, consumed by the user’s friends, popular • When creating a unified list for a given a user reading a specific page, what should be the relative importance of matching the additional stories to the page vs. matching to the user? • Ignoring story context might create offending recommendations • Related direction: Tensor Factorization, Karatzoglou et. al, RecSys’2010 - 19 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 21. Challenge: Incremental Collaborative Filtering • In a live system, we often cannot afford to recompute recommendations regularly over the entire history • Problem: neither neighborhood models nor matrix factorization models easily lend themselves to faithful incremental processing User-Item User-Item User-Item Mi = CF-ALG(ti) Interactions Interactions Interactions t1 t2 t3 ∀f, f { M1, M2 } ≠ CF_ALG(t1∪t2) … T • Is there a model aggregation function f(Mprev, Mcurr) that is “good enough”? - 20 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 22. Challenge: Repeated Recommendations • One typically doesn’t buy the same book twice, nor do people typically read the same news story twice • But people listen to the songs they like over and over again, and watch movies they like multiple times as well • When and how frequently is it ok to recommend an item that was already consumed? • On the other hand, when should we stop showing a recommendation if the user doesn’t act upon it? • Implication: a recommendation system may not only need to track aggregated consumption to-date, – It may need to track consumption timelines – It may need to track recommendation history - 21 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 23. Challenge: Recommending Sets & Sequences of Items • In some domains, users consume multiple items in rapid succession (e.g. music playlists) – Recent works: WWW’2012 (Aizenberg et al., sets) and KDD’2012 (Chen et al., sequences) • From Independent utility of recommendations to set or sequence utility, predicting items that “go well together” – Sometimes need to respect constraints • Tiling recommendations: in TV Watchlist generation, the broadcast schedules further complicates matters due to program overlaps • Perhaps a new domain of constrained recommendations? • Search: result set attributes (e.g. diversity) in Search (Agrawal et al., WSDM’2009) • Netflix tutorial at RecSys’2012: diversity is key @Netflix - 22 - Bangalore/MumbaiConfidential Yahoo! 2013
  • 24. Social Networks and Recommendation Computation • Some are hailing social networks as a silver bullet for recommender systems – Tell me who your friends are and we’ll tell you what you like • Is it really the case that we like the same media as our friends? • Affinity trumps friendship! – There are people out there who are “more like us” than our limited set of friends – Once affinity is considered, the marginal value of social connections is often negligible • Not to be confused with non-friendship social networks, where connections are affinity related (Epinions) - 23 - Bangalore/MumbaiConfidential Yahoo! 2013 RecSys 202
  • 25. Social Networks and Recommendation Consumption • Previous slide nonewithstanding, “social” is a great motivator for consuming recommendations – People like you rate “Lincoln” very highly vs. – Your friends Alice and Bob saw “Lincoln” last night and loved it • Explaining recommendations for motivating and increasing consumption is an emerging practice • Some commercial systems completely separate their explanation generation from their recommendation generation – So Alice and Bob may not be why the system recommended “Lincoln” to you, but they will be leveraged to get you to watch it • Privacy in the face of joint consumption of a personalized experience? - 24 - Bangalore/MumbaiConfidential Yahoo! 2013 RecSys 202
  • 26. Questions, Comments? Thank you! rlempel (at) yahoo-inc dot com - 25 - Yahoo! Confidential