About Our Recommender System

          Kimikazu Kato, Chief Scientist
           Silver Egg Technology Co., Ltd.
Table of Contents

•   About myself
•   About the company and its business
•   Survey on related researches
•   Conclusion




                                         1
About Myself

Kimikazu Kato
• Ph.D in computer science, background in
  mathematics
• Joined Silver Egg as a Chief Scientist in Nov. 2012
• Experiences in numerical computation
  – 3D CAD, geometric computation
  – Computer graphics
  – Partial differential equation
  – Parallel computation, GPGPU
• Now designing the core of recommender system
                                                        2
About Silver Egg Technology




 Silver Egg Technology             Book written by CEO

 Established: September, 1998
 CEO: Tom Foley                 ≪著書≫「One to Oneマーケティングを超えた

 COO: Junko Nishimura           戦略的Webパーソナライゼーション」
                                (出版社:日経BP社 発売:2002年5月)


 Capital: ¥78 Million
 Main Services:                 「ASP・SaaS・ICTアウトソーシングアワード2009」
                                 ASP・SaaS部門「委員長特別賞」受賞
 Recommender System
 Online Advertisement Service
                                第8回(2010)、第9回(2011)
                                「デロイト 日本テクノノロジー Fast50」受賞




                                                                 3
Recommender System


 Recommender system proposes the items best fit for individuals’ needs.
 Good recommender system provides a comfort for online shopping
 experiences and improves customer loyalty.

                                                Ranking
                                                No.1   No.2   No.3


                                    XXXXXX
                                    XXXXXXXXX
                                    3,800円


                      Combination

                                                Additional




                      Cross-sell




                                                                          4
Consistent behavior targeting


Consistent user behavior targeting from “traffic inflow” to “retention” is
essential for improving sales and profit.



     Pre-access                             On-access                                                                                   Post-access


        Traffic inflow                 Service                  Conversion                                  Retention

                                                        Recommender                        Aigent Mail
                                      Aigent
         HotView         Aigent                                                                                         Aigent Gadget       Aigent On-
                                   Personalized                   Aigent     Transaction   Recommender   Event Driven
      Retargeting ad      LPO                     Recommado                                                                 Portal        Demand Printing
                                      Search                   Recommender      Mail           Mail          Mail




                                  Aigent Suite (Real Time Recommender Platform)




                         Silver Egg Technology provides smart targeting technology
                               which enables optimization of online marketing



                                                                                                                                                            5
Interaction of Advertisement and Recommender


                                                         Media                                       Dashboard
                                                                                                                  Merchandizer
                                                                                                                  -Registers items to promote
          Consumer                                                                                                - Checks performance
                                  Discovery in a
                                  media site
                                                                          Shows ads of items to
                                                                          promote to the target
                                                                          users




                                                                               HotView               -   Timestamp
                                                                                                     -   Geographic information
                                                                                                     -   Use behavior
                                                                                                     -   Demands
                                                   To the shopping site                              -   Contexts (search words)



                                     百貨店
                                                                               Aigent
To the site they are interested      通販カタログ                                                              Aigent Suite
                                     ブティック
                                                                            Recommendation for
                                     TVショッピング                               up-sell and cross-sell

                                     アパレル

                                                        Retailer

 Ad contents based on users behaviors in shopping sites are more likely to attract
             attentions and effectively lead users back to those sites
                                                                                                                                            6
Mechanism

       Aigent server
                                                          Client’s EC site


                             “Who bought what”
   Stored and analyzed

                           “Who is browsing what”
  Respond in real time
                         “What should be recommended”

     ASP service                                              +
                            Batch update of inventory
                                                        Code snippet to connect
                                                        with AIgent
  Characteristics:
  • Real time response
  • Implemented as an add-on (cost efficient)


                                                                                  7
Consulting Services

• Just showing the result of mathematical
  computation is not enough
• To extract optimal sales, parameters should be
  tuned by hand
  – Statistical co-relation is not all that matters.
• Sometimes recommendations should reflect some
  “intention”
  – According to policy, strategy, etc.
• Continuous monitoring and A/B testing

                                                       8
About recommendation algorithms

• Collaborative filtering
• Fruitful methods as a result of Netfilx Prize
  – Neighborhood Models
  – Matrix factorization
  – Restricted Boltzmann Machines




                                                  9
Netflix Prize

    The Netflix Prize was an open competition for the best collaborative filtering
    algorithm to predict user ratings for films, based on previous ratings
                                                               — Wikipedia

      Netflix provided open data for this competition




                                   Closed in 2009

                                                                                     10
Movie Rating Prediction

          Each user gives rating to the movies they saw
                     movie
                    user     W       X      Y      Z
                      A      5       4      1      4
                      B      4
                      C              2      3
                      D      1              4      ?



  Is it possible to predict the rating of unknown user/movie pair?


            Ratings are expressed as a sparse matrix.
            A zero value of the matrix doesn’t really mean “zero” but “unknown”



                                                                                  11
Probabilistic Matrix Factorization
        Regarding ratings are expressed by small number of components




             𝐴                   𝑈𝑇                   𝑉                 noise




     Approximate only the non-zero elements




                                                                                12
According to Bayes’ theorem,




              Minimize this objective function


                                                 13
Rating vs Purchase

  Movie rating                                      Purchase recommendation
   movie                                              item
  user      W        X       Y           Z          user       W       X        Y       Z
    A       5        4       1           4             A       1       1        1       1
    B       4                                          B       1
    C                2       3                         C               1
    D       1                4           ?             D       1                1       ?

  Predicts the rating for the user and               Predicts how likely the user buy the
  movie pair.                                        item
  The matrix includes negative feedback               No negative feedback
  (Some movies are rated as “boring”)                 (No reason is given for missing elements)
                                                       => Strong bias toward 1
                                                      Only one kind of value for known elements
                                                       => Gives more degree of freedom

                  A method successful in movie rating prediction is not
                  useful for recommendation of usual shopping site.
                                                                                                  14
Solutions

• Regard a zero element as a negative feedback
  – Too ad hoc but better than naïve PMF
• Assume a certain ratio of zero elements becomes
  one at the optimum [Sindhwani et al. 2010]
  – Assign other variables to zero elements and solve a
    relaxed optimization
  – Experimentally outperform the “zero-as-negative”
    method.


  V.Sindhwani et al., One-Class Matrix Completion with Low-Density Factorizations. In Proc. of ICDM
  2010: 1055-1060
                                                                                                      15
Minimize




Subject to:




       Solve this relaxed problem for non-negative variables
                                                               16
Conclusion

• Scientific approach is important
  – Math really makes money
• But that alone is not enough for real business
• Engineering matters
  – Efficient platform and easy-to-deploy mechanism
• Hand tuning part always remains
  – Consulting for parameter tune is essential




                                                      17

About Our Recommender System

  • 1.
    About Our RecommenderSystem Kimikazu Kato, Chief Scientist Silver Egg Technology Co., Ltd.
  • 2.
    Table of Contents • About myself • About the company and its business • Survey on related researches • Conclusion 1
  • 3.
    About Myself Kimikazu Kato •Ph.D in computer science, background in mathematics • Joined Silver Egg as a Chief Scientist in Nov. 2012 • Experiences in numerical computation – 3D CAD, geometric computation – Computer graphics – Partial differential equation – Parallel computation, GPGPU • Now designing the core of recommender system 2
  • 4.
    About Silver EggTechnology Silver Egg Technology Book written by CEO Established: September, 1998 CEO: Tom Foley ≪著書≫「One to Oneマーケティングを超えた COO: Junko Nishimura 戦略的Webパーソナライゼーション」 (出版社:日経BP社 発売:2002年5月) Capital: ¥78 Million Main Services: 「ASP・SaaS・ICTアウトソーシングアワード2009」 ASP・SaaS部門「委員長特別賞」受賞 Recommender System Online Advertisement Service 第8回(2010)、第9回(2011) 「デロイト 日本テクノノロジー Fast50」受賞 3
  • 5.
    Recommender System Recommendersystem proposes the items best fit for individuals’ needs. Good recommender system provides a comfort for online shopping experiences and improves customer loyalty. Ranking No.1 No.2 No.3 XXXXXX XXXXXXXXX 3,800円 Combination Additional Cross-sell 4
  • 6.
    Consistent behavior targeting Consistentuser behavior targeting from “traffic inflow” to “retention” is essential for improving sales and profit. Pre-access On-access Post-access Traffic inflow Service Conversion Retention Recommender Aigent Mail Aigent HotView Aigent Aigent Gadget Aigent On- Personalized Aigent Transaction Recommender Event Driven Retargeting ad LPO Recommado Portal Demand Printing Search Recommender Mail Mail Mail Aigent Suite (Real Time Recommender Platform) Silver Egg Technology provides smart targeting technology which enables optimization of online marketing 5
  • 7.
    Interaction of Advertisementand Recommender Media Dashboard Merchandizer -Registers items to promote Consumer - Checks performance Discovery in a media site Shows ads of items to promote to the target users HotView - Timestamp - Geographic information - Use behavior - Demands To the shopping site - Contexts (search words) 百貨店 Aigent To the site they are interested 通販カタログ Aigent Suite ブティック Recommendation for TVショッピング up-sell and cross-sell アパレル Retailer Ad contents based on users behaviors in shopping sites are more likely to attract attentions and effectively lead users back to those sites 6
  • 8.
    Mechanism Aigent server Client’s EC site “Who bought what” Stored and analyzed “Who is browsing what” Respond in real time “What should be recommended” ASP service + Batch update of inventory Code snippet to connect with AIgent Characteristics: • Real time response • Implemented as an add-on (cost efficient) 7
  • 9.
    Consulting Services • Justshowing the result of mathematical computation is not enough • To extract optimal sales, parameters should be tuned by hand – Statistical co-relation is not all that matters. • Sometimes recommendations should reflect some “intention” – According to policy, strategy, etc. • Continuous monitoring and A/B testing 8
  • 10.
    About recommendation algorithms •Collaborative filtering • Fruitful methods as a result of Netfilx Prize – Neighborhood Models – Matrix factorization – Restricted Boltzmann Machines 9
  • 11.
    Netflix Prize The Netflix Prize was an open competition for the best collaborative filtering algorithm to predict user ratings for films, based on previous ratings — Wikipedia Netflix provided open data for this competition Closed in 2009 10
  • 12.
    Movie Rating Prediction Each user gives rating to the movies they saw movie user W X Y Z A 5 4 1 4 B 4 C 2 3 D 1 4 ? Is it possible to predict the rating of unknown user/movie pair? Ratings are expressed as a sparse matrix. A zero value of the matrix doesn’t really mean “zero” but “unknown” 11
  • 13.
    Probabilistic Matrix Factorization Regarding ratings are expressed by small number of components 𝐴 𝑈𝑇 𝑉 noise Approximate only the non-zero elements 12
  • 14.
    According to Bayes’theorem, Minimize this objective function 13
  • 15.
    Rating vs Purchase Movie rating Purchase recommendation movie item user W X Y Z user W X Y Z A 5 4 1 4 A 1 1 1 1 B 4 B 1 C 2 3 C 1 D 1 4 ? D 1 1 ? Predicts the rating for the user and Predicts how likely the user buy the movie pair. item The matrix includes negative feedback No negative feedback (Some movies are rated as “boring”) (No reason is given for missing elements) => Strong bias toward 1 Only one kind of value for known elements => Gives more degree of freedom A method successful in movie rating prediction is not useful for recommendation of usual shopping site. 14
  • 16.
    Solutions • Regard azero element as a negative feedback – Too ad hoc but better than naïve PMF • Assume a certain ratio of zero elements becomes one at the optimum [Sindhwani et al. 2010] – Assign other variables to zero elements and solve a relaxed optimization – Experimentally outperform the “zero-as-negative” method. V.Sindhwani et al., One-Class Matrix Completion with Low-Density Factorizations. In Proc. of ICDM 2010: 1055-1060 15
  • 17.
    Minimize Subject to: Solve this relaxed problem for non-negative variables 16
  • 18.
    Conclusion • Scientific approachis important – Math really makes money • But that alone is not enough for real business • Engineering matters – Efficient platform and easy-to-deploy mechanism • Hand tuning part always remains – Consulting for parameter tune is essential 17