SlideShare a Scribd company logo
1 of 18
Download to read offline
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

More Related Content

What's hot

Business Model Canvas (workshop at IIM Ahmedabad)
Business Model Canvas (workshop at IIM Ahmedabad)Business Model Canvas (workshop at IIM Ahmedabad)
Business Model Canvas (workshop at IIM Ahmedabad)Nagarjun Kandukuru
 
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...graemeknows
 
Location Based Services von Volker Hoyer
Location Based Services von Volker HoyerLocation Based Services von Volker Hoyer
Location Based Services von Volker HoyerADTELLIGENCE GmbH
 
Translating Pricing Theory into Reality
Translating Pricing Theory into RealityTranslating Pricing Theory into Reality
Translating Pricing Theory into RealityJDA Software
 
What Can Bond Do For Your Company
What Can Bond Do For Your CompanyWhat Can Bond Do For Your Company
What Can Bond Do For Your Companybirney.james
 
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...B com Expo | GL events Italia
 
Marcelo cabane ibm - ecommerce day
Marcelo cabane   ibm - ecommerce day Marcelo cabane   ibm - ecommerce day
Marcelo cabane ibm - ecommerce day Marcos Pueyrredon
 
Customer experience letter Bank of America thoughts
Customer experience letter Bank of America thoughtsCustomer experience letter Bank of America thoughts
Customer experience letter Bank of America thoughtsClient X Client
 
Services Presentation by Insight
Services Presentation by InsightServices Presentation by Insight
Services Presentation by InsightHayk Ghazaryan
 
Retail CXO Roundtable - Strategies For Digital Transformation
Retail CXO Roundtable - Strategies For Digital TransformationRetail CXO Roundtable - Strategies For Digital Transformation
Retail CXO Roundtable - Strategies For Digital TransformationG3 Communications
 
Putting Customers at the Heart, Mark Iremonger
Putting Customers at the Heart, Mark IremongerPutting Customers at the Heart, Mark Iremonger
Putting Customers at the Heart, Mark IremongeriCrossing
 
Connectedness Gets Personal - Adam Lavelle - iCrossing
Connectedness Gets Personal - Adam Lavelle - iCrossingConnectedness Gets Personal - Adam Lavelle - iCrossing
Connectedness Gets Personal - Adam Lavelle - iCrossingiCrossing
 
How to Quantumly Grow your Ecommerce Business - Strategies and Tactics
How to Quantumly Grow your Ecommerce Business - Strategies and TacticsHow to Quantumly Grow your Ecommerce Business - Strategies and Tactics
How to Quantumly Grow your Ecommerce Business - Strategies and TacticsGoECart
 
Brand Positioning
Brand PositioningBrand Positioning
Brand Positioningzirram
 
Internet Week Yahoo! Academy: How Direct Can You Be?
Internet Week Yahoo! Academy: How Direct Can You Be?Internet Week Yahoo! Academy: How Direct Can You Be?
Internet Week Yahoo! Academy: How Direct Can You Be?YahooUK
 
Ray Anderson Virtual Goods Forum presentation, 24 June 2010
Ray Anderson Virtual Goods Forum presentation, 24 June 2010Ray Anderson Virtual Goods Forum presentation, 24 June 2010
Ray Anderson Virtual Goods Forum presentation, 24 June 2010Bango
 
How to increase Inbound Campaign results
How to increase Inbound Campaign resultsHow to increase Inbound Campaign results
How to increase Inbound Campaign resultsJohn Timmerman
 

What's hot (20)

#dd12 WebSphere Commerce + WCM
#dd12 WebSphere Commerce + WCM#dd12 WebSphere Commerce + WCM
#dd12 WebSphere Commerce + WCM
 
Business Model Canvas (workshop at IIM Ahmedabad)
Business Model Canvas (workshop at IIM Ahmedabad)Business Model Canvas (workshop at IIM Ahmedabad)
Business Model Canvas (workshop at IIM Ahmedabad)
 
Power Of Analytics
Power Of AnalyticsPower Of Analytics
Power Of Analytics
 
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...
Big Data, Bigger Campaigns: Using IBM’s Unica and Netezza Platforms to Increa...
 
Location Based Services von Volker Hoyer
Location Based Services von Volker HoyerLocation Based Services von Volker Hoyer
Location Based Services von Volker Hoyer
 
Translating Pricing Theory into Reality
Translating Pricing Theory into RealityTranslating Pricing Theory into Reality
Translating Pricing Theory into Reality
 
What Can Bond Do For Your Company
What Can Bond Do For Your CompanyWhat Can Bond Do For Your Company
What Can Bond Do For Your Company
 
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...
B com 2013 | Intershop 7, flessibilità tecnologica per un mercato in divenire...
 
Marcelo cabane ibm - ecommerce day
Marcelo cabane   ibm - ecommerce day Marcelo cabane   ibm - ecommerce day
Marcelo cabane ibm - ecommerce day
 
Self-service: Optimice cada interacción con el cliente - Ana del Amo, Oracle
Self-service: Optimice cada interacción con el cliente - Ana del Amo, OracleSelf-service: Optimice cada interacción con el cliente - Ana del Amo, Oracle
Self-service: Optimice cada interacción con el cliente - Ana del Amo, Oracle
 
Customer experience letter Bank of America thoughts
Customer experience letter Bank of America thoughtsCustomer experience letter Bank of America thoughts
Customer experience letter Bank of America thoughts
 
Services Presentation by Insight
Services Presentation by InsightServices Presentation by Insight
Services Presentation by Insight
 
Retail CXO Roundtable - Strategies For Digital Transformation
Retail CXO Roundtable - Strategies For Digital TransformationRetail CXO Roundtable - Strategies For Digital Transformation
Retail CXO Roundtable - Strategies For Digital Transformation
 
Putting Customers at the Heart, Mark Iremonger
Putting Customers at the Heart, Mark IremongerPutting Customers at the Heart, Mark Iremonger
Putting Customers at the Heart, Mark Iremonger
 
Connectedness Gets Personal - Adam Lavelle - iCrossing
Connectedness Gets Personal - Adam Lavelle - iCrossingConnectedness Gets Personal - Adam Lavelle - iCrossing
Connectedness Gets Personal - Adam Lavelle - iCrossing
 
How to Quantumly Grow your Ecommerce Business - Strategies and Tactics
How to Quantumly Grow your Ecommerce Business - Strategies and TacticsHow to Quantumly Grow your Ecommerce Business - Strategies and Tactics
How to Quantumly Grow your Ecommerce Business - Strategies and Tactics
 
Brand Positioning
Brand PositioningBrand Positioning
Brand Positioning
 
Internet Week Yahoo! Academy: How Direct Can You Be?
Internet Week Yahoo! Academy: How Direct Can You Be?Internet Week Yahoo! Academy: How Direct Can You Be?
Internet Week Yahoo! Academy: How Direct Can You Be?
 
Ray Anderson Virtual Goods Forum presentation, 24 June 2010
Ray Anderson Virtual Goods Forum presentation, 24 June 2010Ray Anderson Virtual Goods Forum presentation, 24 June 2010
Ray Anderson Virtual Goods Forum presentation, 24 June 2010
 
How to increase Inbound Campaign results
How to increase Inbound Campaign resultsHow to increase Inbound Campaign results
How to increase Inbound Campaign results
 

Viewers also liked

Recommendation System --Theory and Practice
Recommendation System --Theory and PracticeRecommendation System --Theory and Practice
Recommendation System --Theory and PracticeKimikazu Kato
 
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...Kimikazu Kato
 
A Safe Rule for Sparse Logistic Regression
A Safe Rule for Sparse Logistic RegressionA Safe Rule for Sparse Logistic Regression
A Safe Rule for Sparse Logistic RegressionKimikazu Kato
 
特定の不快感を与えるツイートの分類と自動生成について
特定の不快感を与えるツイートの分類と自動生成について特定の不快感を与えるツイートの分類と自動生成について
特定の不快感を与えるツイートの分類と自動生成についてKimikazu Kato
 
Effective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyEffective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyKimikazu Kato
 

Viewers also liked (7)

Recommendation System --Theory and Practice
Recommendation System --Theory and PracticeRecommendation System --Theory and Practice
Recommendation System --Theory and Practice
 
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...
【論文紹介】Approximate Bayesian Image Interpretation Using Generative Probabilisti...
 
Zuang-FPSGD
Zuang-FPSGDZuang-FPSGD
Zuang-FPSGD
 
A Safe Rule for Sparse Logistic Regression
A Safe Rule for Sparse Logistic RegressionA Safe Rule for Sparse Logistic Regression
A Safe Rule for Sparse Logistic Regression
 
特定の不快感を与えるツイートの分類と自動生成について
特定の不快感を与えるツイートの分類と自動生成について特定の不快感を与えるツイートの分類と自動生成について
特定の不快感を与えるツイートの分類と自動生成について
 
養成読本と私
養成読本と私養成読本と私
養成読本と私
 
Effective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyEffective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPy
 

Similar to About Our Recommender System

Van surfer naar koper en terug connecting the dots
Van surfer naar koper en terug connecting the dotsVan surfer naar koper en terug connecting the dots
Van surfer naar koper en terug connecting the dotsBisnode Belgium
 
Engage 2013 - Webtrends Streams
Engage 2013 - Webtrends StreamsEngage 2013 - Webtrends Streams
Engage 2013 - Webtrends StreamsWebtrends
 
How Hansa Cequity can help you enrich your Customer Equity?
How Hansa Cequity can help you enrich your Customer Equity?How Hansa Cequity can help you enrich your Customer Equity?
How Hansa Cequity can help you enrich your Customer Equity?Ajay Kelkar
 
Pianificazione strategica per la creazione di un Global E-Commerce
Pianificazione strategica per la creazione di un Global E-CommercePianificazione strategica per la creazione di un Global E-Commerce
Pianificazione strategica per la creazione di un Global E-CommerceFederico Gasparotto
 
DIBS: Webinar for dummies
DIBS: Webinar for dummiesDIBS: Webinar for dummies
DIBS: Webinar for dummiesÅsa Jonsson
 
Cgc2 cdn gamingsummit-real-time-customer-analytics
Cgc2 cdn gamingsummit-real-time-customer-analyticsCgc2 cdn gamingsummit-real-time-customer-analytics
Cgc2 cdn gamingsummit-real-time-customer-analyticsbrock55
 
SAP's Excellence in Integrated Marketing: Converting Online Traffic to Leads
SAP's Excellence in Integrated Marketing: Converting Online Traffic to LeadsSAP's Excellence in Integrated Marketing: Converting Online Traffic to Leads
SAP's Excellence in Integrated Marketing: Converting Online Traffic to LeadsVivastream
 
Atosho Conference March 2013 Anders Ibsen
Atosho Conference March 2013 Anders IbsenAtosho Conference March 2013 Anders Ibsen
Atosho Conference March 2013 Anders Ibsentroelsatosho
 
Vijay kusurkar value chain stratagem
Vijay kusurkar value chain stratagemVijay kusurkar value chain stratagem
Vijay kusurkar value chain stratagemECR Community
 
2009 06 03 Lima Consulting Alans Comments
2009 06 03 Lima Consulting   Alans Comments2009 06 03 Lima Consulting   Alans Comments
2009 06 03 Lima Consulting Alans CommentsLima Consulting Group
 
SunCorp Analytics
SunCorp AnalyticsSunCorp Analytics
SunCorp AnalyticsDatalicious
 
Conversion Conference - What's in YOUR toolkit?
Conversion Conference - What's in YOUR toolkit?Conversion Conference - What's in YOUR toolkit?
Conversion Conference - What's in YOUR toolkit?Craig Sullivan
 
IT PULP Ecommerce Consultancy
IT PULP Ecommerce ConsultancyIT PULP Ecommerce Consultancy
IT PULP Ecommerce ConsultancyIT PULP
 
Online Proposition & Sales Flow Automotive | Douglas & Breitner
Online Proposition & Sales Flow Automotive | Douglas & Breitner Online Proposition & Sales Flow Automotive | Douglas & Breitner
Online Proposition & Sales Flow Automotive | Douglas & Breitner Stephan Schroeders (+31 645600507)
 
Partner marketing 22 march
Partner marketing 22 marchPartner marketing 22 march
Partner marketing 22 marchRob Bartlett
 

Similar to About Our Recommender System (20)

Van surfer naar koper en terug connecting the dots
Van surfer naar koper en terug connecting the dotsVan surfer naar koper en terug connecting the dots
Van surfer naar koper en terug connecting the dots
 
Engage 2013 - Webtrends Streams
Engage 2013 - Webtrends StreamsEngage 2013 - Webtrends Streams
Engage 2013 - Webtrends Streams
 
How Hansa Cequity can help you enrich your Customer Equity?
How Hansa Cequity can help you enrich your Customer Equity?How Hansa Cequity can help you enrich your Customer Equity?
How Hansa Cequity can help you enrich your Customer Equity?
 
Pianificazione strategica per la creazione di un Global E-Commerce
Pianificazione strategica per la creazione di un Global E-CommercePianificazione strategica per la creazione di un Global E-Commerce
Pianificazione strategica per la creazione di un Global E-Commerce
 
DIBS: Webinar for dummies
DIBS: Webinar for dummiesDIBS: Webinar for dummies
DIBS: Webinar for dummies
 
BTFV
BTFVBTFV
BTFV
 
Cgc2 cdn gamingsummit-real-time-customer-analytics
Cgc2 cdn gamingsummit-real-time-customer-analyticsCgc2 cdn gamingsummit-real-time-customer-analytics
Cgc2 cdn gamingsummit-real-time-customer-analytics
 
SAP's Excellence in Integrated Marketing: Converting Online Traffic to Leads
SAP's Excellence in Integrated Marketing: Converting Online Traffic to LeadsSAP's Excellence in Integrated Marketing: Converting Online Traffic to Leads
SAP's Excellence in Integrated Marketing: Converting Online Traffic to Leads
 
Mobile Analytics
Mobile AnalyticsMobile Analytics
Mobile Analytics
 
Mobile Analytics
Mobile Analytics Mobile Analytics
Mobile Analytics
 
Atosho Conference March 2013 Anders Ibsen
Atosho Conference March 2013 Anders IbsenAtosho Conference March 2013 Anders Ibsen
Atosho Conference March 2013 Anders Ibsen
 
Vijay kusurkar value chain stratagem
Vijay kusurkar value chain stratagemVijay kusurkar value chain stratagem
Vijay kusurkar value chain stratagem
 
2009 06 03 Lima Consulting Alans Comments
2009 06 03 Lima Consulting   Alans Comments2009 06 03 Lima Consulting   Alans Comments
2009 06 03 Lima Consulting Alans Comments
 
SunCorp Analytics
SunCorp AnalyticsSunCorp Analytics
SunCorp Analytics
 
Conversion Conference - What's in YOUR toolkit?
Conversion Conference - What's in YOUR toolkit?Conversion Conference - What's in YOUR toolkit?
Conversion Conference - What's in YOUR toolkit?
 
IT PULP Ecommerce Consultancy
IT PULP Ecommerce ConsultancyIT PULP Ecommerce Consultancy
IT PULP Ecommerce Consultancy
 
Online Proposition & Sales Flow Automotive | Douglas & Breitner
Online Proposition & Sales Flow Automotive | Douglas & Breitner Online Proposition & Sales Flow Automotive | Douglas & Breitner
Online Proposition & Sales Flow Automotive | Douglas & Breitner
 
Biz Model for AtracTable
Biz Model for AtracTableBiz Model for AtracTable
Biz Model for AtracTable
 
Developing Social Media as a Sales Channel
Developing Social Media as a Sales ChannelDeveloping Social Media as a Sales Channel
Developing Social Media as a Sales Channel
 
Partner marketing 22 march
Partner marketing 22 marchPartner marketing 22 march
Partner marketing 22 march
 

More from Kimikazu Kato

Tokyo webmining 2017-10-28
Tokyo webmining 2017-10-28Tokyo webmining 2017-10-28
Tokyo webmining 2017-10-28Kimikazu Kato
 
機械学習ゴリゴリ派のための数学とPython
機械学習ゴリゴリ派のための数学とPython機械学習ゴリゴリ派のための数学とPython
機械学習ゴリゴリ派のための数学とPythonKimikazu Kato
 
Pythonを使った機械学習の学習
Pythonを使った機械学習の学習Pythonを使った機械学習の学習
Pythonを使った機械学習の学習Kimikazu Kato
 
Fast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansKimikazu Kato
 
Pythonで機械学習入門以前
Pythonで機械学習入門以前Pythonで機械学習入門以前
Pythonで機械学習入門以前Kimikazu Kato
 
Pythonによる機械学習
Pythonによる機械学習Pythonによる機械学習
Pythonによる機械学習Kimikazu Kato
 
Introduction to behavior based recommendation system
Introduction to behavior based recommendation systemIntroduction to behavior based recommendation system
Introduction to behavior based recommendation systemKimikazu Kato
 
Pythonによる機械学習の最前線
Pythonによる機械学習の最前線Pythonによる機械学習の最前線
Pythonによる機械学習の最前線Kimikazu Kato
 
Sparse pca via bipartite matching
Sparse pca via bipartite matchingSparse pca via bipartite matching
Sparse pca via bipartite matchingKimikazu Kato
 
正しいプログラミング言語の覚え方
正しいプログラミング言語の覚え方正しいプログラミング言語の覚え方
正しいプログラミング言語の覚え方Kimikazu Kato
 
Introduction to NumPy for Machine Learning Programmers
Introduction to NumPy for Machine Learning ProgrammersIntroduction to NumPy for Machine Learning Programmers
Introduction to NumPy for Machine Learning ProgrammersKimikazu Kato
 
ネット通販向けレコメンドシステム提供サービスについて
ネット通販向けレコメンドシステム提供サービスについてネット通販向けレコメンドシステム提供サービスについて
ネット通販向けレコメンドシステム提供サービスについてKimikazu Kato
 
関東GPGPU勉強会資料
関東GPGPU勉強会資料関東GPGPU勉強会資料
関東GPGPU勉強会資料Kimikazu Kato
 
2012-03-08 MSS研究会
2012-03-08 MSS研究会2012-03-08 MSS研究会
2012-03-08 MSS研究会Kimikazu Kato
 
純粋関数型アルゴリズム入門
純粋関数型アルゴリズム入門純粋関数型アルゴリズム入門
純粋関数型アルゴリズム入門Kimikazu Kato
 

More from Kimikazu Kato (16)

Tokyo webmining 2017-10-28
Tokyo webmining 2017-10-28Tokyo webmining 2017-10-28
Tokyo webmining 2017-10-28
 
機械学習ゴリゴリ派のための数学とPython
機械学習ゴリゴリ派のための数学とPython機械学習ゴリゴリ派のための数学とPython
機械学習ゴリゴリ派のための数学とPython
 
Pythonを使った機械学習の学習
Pythonを使った機械学習の学習Pythonを使った機械学習の学習
Pythonを使った機械学習の学習
 
Fast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-MeansFast and Probvably Seedings for k-Means
Fast and Probvably Seedings for k-Means
 
Pythonで機械学習入門以前
Pythonで機械学習入門以前Pythonで機械学習入門以前
Pythonで機械学習入門以前
 
Pythonによる機械学習
Pythonによる機械学習Pythonによる機械学習
Pythonによる機械学習
 
Introduction to behavior based recommendation system
Introduction to behavior based recommendation systemIntroduction to behavior based recommendation system
Introduction to behavior based recommendation system
 
Pythonによる機械学習の最前線
Pythonによる機械学習の最前線Pythonによる機械学習の最前線
Pythonによる機械学習の最前線
 
Sparse pca via bipartite matching
Sparse pca via bipartite matchingSparse pca via bipartite matching
Sparse pca via bipartite matching
 
正しいプログラミング言語の覚え方
正しいプログラミング言語の覚え方正しいプログラミング言語の覚え方
正しいプログラミング言語の覚え方
 
Introduction to NumPy for Machine Learning Programmers
Introduction to NumPy for Machine Learning ProgrammersIntroduction to NumPy for Machine Learning Programmers
Introduction to NumPy for Machine Learning Programmers
 
Sapporo20140709
Sapporo20140709Sapporo20140709
Sapporo20140709
 
ネット通販向けレコメンドシステム提供サービスについて
ネット通販向けレコメンドシステム提供サービスについてネット通販向けレコメンドシステム提供サービスについて
ネット通販向けレコメンドシステム提供サービスについて
 
関東GPGPU勉強会資料
関東GPGPU勉強会資料関東GPGPU勉強会資料
関東GPGPU勉強会資料
 
2012-03-08 MSS研究会
2012-03-08 MSS研究会2012-03-08 MSS研究会
2012-03-08 MSS研究会
 
純粋関数型アルゴリズム入門
純粋関数型アルゴリズム入門純粋関数型アルゴリズム入門
純粋関数型アルゴリズム入門
 

Recently uploaded

Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfLoriGlavin3
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESmohitsingh558521
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.Curtis Poe
 

Recently uploaded (20)

Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Moving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdfMoving Beyond Passwords: FIDO Paris Seminar.pdf
Moving Beyond Passwords: FIDO Paris Seminar.pdf
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICESSALESFORCE EDUCATION CLOUD | FEXLE SERVICES
SALESFORCE EDUCATION CLOUD | FEXLE SERVICES
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.How AI, OpenAI, and ChatGPT impact business and software.
How AI, OpenAI, and ChatGPT impact business and software.
 

About Our Recommender System

  • 1. About Our Recommender System 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 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
  • 5. 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
  • 6. 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
  • 7. 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
  • 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 • 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
  • 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 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
  • 17. Minimize Subject to: Solve this relaxed problem for non-negative variables 16
  • 18. 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