SlideShare ist ein Scribd-Unternehmen logo
1 von 22
From a toolkit of
recommendation algorithms
into a real business:
the Gravity R&D experience




13.09.2012.
The kick-start




2   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Facing with real needs

    What we had                                                  What clients wanted
    • rating prediction algorithms • recommendations that
    • coded in various languages     bring revenue
    • blending mechanism           • robustness
    • accuracy oriented            • low response time
                                   • easy integration
                                   • reporting




3   From a toolkit of recommendation algorithms into a real business   13.09.2012.
What we do?




          users


                                                                       content of service
                                                                           provider
                               recommender
4   From a toolkit of recommendation algorithms into a real business    13.09.2012.
Explicit vs implicit feedback

    No ratings but interactions




    sparse vs. dense matrix



    requires different learning

5   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Increase revenue: A/B tests

    against the original solution




    internally




6   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Robustness


                                                                                                  Management LAN

                                                                                    SNMP
                                                                                                                          Nagios Monitoring     HP OpenView
                                                                                                                             Aggregator


                                                              HTTP                         HTTP
    Platform OSS/BSS                                          / SQL                        / SQL
                                              IMPRESS                   IMPRESS
        SOAP                            Application Server #1     Application Server #2
                                                                                                       IMPRESS Frontend
                                                                                                         web server #1
          Backend LAN                                      Reco LAN                        HTTP                                 Load Balancer   HTTP(S)


                             Firewall                   SQL             SQL
        CSV over FTP
                                                                                                                                    TV Service LAN
                                                                                                      IMPRESS Frontend
                                                                                                        web server #2

                                                   Database #1        Database #2
Reporting Subsystem




                                                                                                                   End users


7    From a toolkit of recommendation algorithms into a real business                             13.09.2012.
Time requirements

    • Response time: few ms (max 200)
    • Training time: maximum few hours
      • regular retraining
      • incremental training
    • Newsletters:
      • nightly batch run




8   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Productization



              IMPRESS                                     RECO                       AD•APT
             for                                          for                            for
    IPTV, CATV and satellite                          e-commerce                 ad networks and ad
                                                                                  server providers


         Recommends                                Recommends                Recommends Personally
                                                 Personally Relevant              Relevant
      Personally Relevant
                                                products & services                 ads
        Linear TV, VOD,
     catch-up TV and more



                                Gravity personalization platform

9   From a toolkit of recommendation algorithms into a real business   13.09.2012.
The 5% question – Importance of UI

     Francisco Martin (Strands): „the algorithm is only 5% in the success of
     the recommender system”
     • placement
         below or above the fold
         scrolling
         easy to recognize
         floating in
     • title
         not misleading
         explanation like
     • widget
         carrousel
         static

10   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Recommendation scenario


                                                                                          Item2Item
                                                                                      recommendation
                                                                                        logic: the ad’s
                                                                                         profile will be
                                                                                       matched to the
                                                                                       profile model of
                                                                                         available ads




11   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Marketing channels




        Changing the order of two boxes: 25% CTR increase

12   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Cannibalization

     • Goal: increase user engagement
     • Measurements
       • average visit length
       • average page views
     • Effect of accurate recommendations:
       • use of listing page ↓
       • use of item page ↑
     • Overall page view: remains the same
     • Secondary measurements
       • Contacting
       • CTR increase




13   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Evolution: increased user engagement




     • not a cold start problem
     • parameter optimization and user engagement




14   From a toolkit of recommendation algorithms into a real business   13.09.2012.
KPIs – may change during testing




15   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Complete personalization: coupon-world

     • Newsletter (daily +
       occassionally)
     • Ranking all offers on the website
        • top1 item
        • category preferences



                                                                  • user metadata (gender, age, …)
                                                                  • user category preferences
                                                                    (seldom given)
                                                                  • item metadata
                                                                  • context

                                                                  • customer vs. vendor

16   From a toolkit of recommendation algorithms into a real business     13.09.2012.
Business rules – driving/overriding ranking




17   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Contexts




18   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Context at TV program recommendation

     • TV (EPG program & video-on-demand)
        explicit and implicit identification of the user in the household
        time-dependent recommendation




19   From a toolkit of recommendation algorithms into a real business   13.09.2012.
(offline)
     Some results (online)

                                  Improvement using season
                                  iTALS              iTALSx
                   Dataset Recall@20 MAP@20 Recall@20 MAP@20
                  Grocery     64,31% 137,96%     89,99% 199,82%
                  TV1         14,77% 43,80%      28,66% 85,33%
                  TV2         -7,94% 10,69%       7,77% 14,15%
                  LastFM      96,10% 116,54%     40,98% 254,62%

                                    Improvement using Seq
                                  iTALS               iTALSx
                   Dataset Recall@20 MAP@20 Recall@20 MAP@20
                  Grocery     84,48% 104,13% 108,83% 122,24%
                  TV1         36,15% 55,07%       26,14% 29,93%

20   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Anecdotes

     • Item2item recommendations – bookstore


     • Placebo effect


     • buyer vs. seller


21   From a toolkit of recommendation algorithms into a real business   13.09.2012.
Conclusion

     • Offline and online testing


     • From simple to sophisticated


     • Many more potential fields of application



22   From a toolkit of recommendation algorithms into a real business   13.09.2012.

Weitere ähnliche Inhalte

Was ist angesagt?

Cw13 aws by tamer abdul radi-cloud9ners
Cw13 aws by tamer abdul radi-cloud9nersCw13 aws by tamer abdul radi-cloud9ners
Cw13 aws by tamer abdul radi-cloud9ners
TheInevitableCloud
 

Was ist angesagt? (20)

ASTQB washington-sept-2015
ASTQB washington-sept-2015ASTQB washington-sept-2015
ASTQB washington-sept-2015
 
Creating a Culture of Cost Management in Your Organization – J.R. Storment, C...
Creating a Culture of Cost Management in Your Organization – J.R. Storment, C...Creating a Culture of Cost Management in Your Organization – J.R. Storment, C...
Creating a Culture of Cost Management in Your Organization – J.R. Storment, C...
 
(ISM309) Efficient Innovation:High-Velocity Cost Management at Netflix
(ISM309) Efficient Innovation:High-Velocity Cost Management at Netflix(ISM309) Efficient Innovation:High-Velocity Cost Management at Netflix
(ISM309) Efficient Innovation:High-Velocity Cost Management at Netflix
 
12 Ways to Manage Cloud Costs and Optimize Cloud Spend
12 Ways to Manage Cloud Costs and Optimize Cloud Spend12 Ways to Manage Cloud Costs and Optimize Cloud Spend
12 Ways to Manage Cloud Costs and Optimize Cloud Spend
 
GO For A Cloud Certification (AWS)
GO For A Cloud Certification (AWS)GO For A Cloud Certification (AWS)
GO For A Cloud Certification (AWS)
 
Cw13 aws by tamer abdul radi-cloud9ners
Cw13 aws by tamer abdul radi-cloud9nersCw13 aws by tamer abdul radi-cloud9ners
Cw13 aws by tamer abdul radi-cloud9ners
 
AWS re:Invent 2016: Saving at Scale with Reserved Instances (ENT307)
AWS re:Invent 2016: Saving at Scale with Reserved Instances (ENT307)AWS re:Invent 2016: Saving at Scale with Reserved Instances (ENT307)
AWS re:Invent 2016: Saving at Scale with Reserved Instances (ENT307)
 
AtlasCamp 2014: Stash State of the Union
AtlasCamp 2014: Stash State of the UnionAtlasCamp 2014: Stash State of the Union
AtlasCamp 2014: Stash State of the Union
 
Cut AWS Costs: Using Spot Instances for More Than Batch
Cut AWS Costs: Using Spot Instances for More Than BatchCut AWS Costs: Using Spot Instances for More Than Batch
Cut AWS Costs: Using Spot Instances for More Than Batch
 
Cloud computing: cost reduction
Cloud computing: cost reductionCloud computing: cost reduction
Cloud computing: cost reduction
 
„OWASP Top Ten in Latvia“ by Agris Krusts from IT Centrs SIA at Security focu...
„OWASP Top Ten in Latvia“ by Agris Krusts from IT Centrs SIA at Security focu...„OWASP Top Ten in Latvia“ by Agris Krusts from IT Centrs SIA at Security focu...
„OWASP Top Ten in Latvia“ by Agris Krusts from IT Centrs SIA at Security focu...
 
AWS Cloud Cost Optimization
AWS Cloud Cost OptimizationAWS Cloud Cost Optimization
AWS Cloud Cost Optimization
 
Keep Cloud Transformation on Track: Nine Best Practices to Avoid or Break Thr...
Keep Cloud Transformation on Track: Nine Best Practices to Avoid or Break Thr...Keep Cloud Transformation on Track: Nine Best Practices to Avoid or Break Thr...
Keep Cloud Transformation on Track: Nine Best Practices to Avoid or Break Thr...
 
CloudKey by LicenseConsult Experts
CloudKey by LicenseConsult ExpertsCloudKey by LicenseConsult Experts
CloudKey by LicenseConsult Experts
 
Hybrid Cloud Orchestration: How SuperChoice Does It
Hybrid Cloud Orchestration: How SuperChoice Does ItHybrid Cloud Orchestration: How SuperChoice Does It
Hybrid Cloud Orchestration: How SuperChoice Does It
 
AWS re:Invent 2019 Recap - Expert Virtual Panel - Agile/DevOps/Team Tooling
AWS re:Invent 2019 Recap - Expert Virtual Panel - Agile/DevOps/Team ToolingAWS re:Invent 2019 Recap - Expert Virtual Panel - Agile/DevOps/Team Tooling
AWS re:Invent 2019 Recap - Expert Virtual Panel - Agile/DevOps/Team Tooling
 
AWS re:Invent 2016: Identifying Your Migration Options: the 6 Rs (ENT311)
AWS re:Invent 2016: Identifying Your Migration Options: the 6 Rs (ENT311)AWS re:Invent 2016: Identifying Your Migration Options: the 6 Rs (ENT311)
AWS re:Invent 2016: Identifying Your Migration Options: the 6 Rs (ENT311)
 
Manage and Optimize Cloud Spend with RightScale Optima
Manage and Optimize Cloud Spend with RightScale OptimaManage and Optimize Cloud Spend with RightScale Optima
Manage and Optimize Cloud Spend with RightScale Optima
 
Pivoting to Cloud: How an MSP Brokers Cloud Services
Pivoting to Cloud: How an MSP Brokers Cloud Services Pivoting to Cloud: How an MSP Brokers Cloud Services
Pivoting to Cloud: How an MSP Brokers Cloud Services
 
Meetup ilm virtual emea
Meetup ilm virtual emeaMeetup ilm virtual emea
Meetup ilm virtual emea
 

Andere mochten auch

Gravity rd corporate introduction - nlp matinĂŠ 2014
Gravity rd corporate introduction  - nlp matinĂŠ 2014Gravity rd corporate introduction  - nlp matinĂŠ 2014
Gravity rd corporate introduction - nlp matinĂŠ 2014
Zoltan Varju
 
Gravity personalizaton intro
Gravity personalizaton introGravity personalizaton intro
Gravity personalizaton intro
Eszter Nagy
 

Andere mochten auch (6)

Gravity rd corporate introduction - nlp matinĂŠ 2014
Gravity rd corporate introduction  - nlp matinĂŠ 2014Gravity rd corporate introduction  - nlp matinĂŠ 2014
Gravity rd corporate introduction - nlp matinĂŠ 2014
 
Gravity personalizaton intro
Gravity personalizaton introGravity personalizaton intro
Gravity personalizaton intro
 
Xây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệp
Xây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệpXây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệp
Xây dựng mạng lưới tài năng trẻ trong sáng tạo – khởi nghiệp
 
Entrepreneurship & Innovation: Dual-core Engine
Entrepreneurship & Innovation: Dual-core EngineEntrepreneurship & Innovation: Dual-core Engine
Entrepreneurship & Innovation: Dual-core Engine
 
The rise of Recommendation Engines
The rise of Recommendation EnginesThe rise of Recommendation Engines
The rise of Recommendation Engines
 
Lessons learnt at building recommendation services at industry scale
Lessons learnt at building recommendation services at industry scaleLessons learnt at building recommendation services at industry scale
Lessons learnt at building recommendation services at industry scale
 

Ähnlich wie From a toolkit of recommendation algorithms into a real business: the Gravity R&D experience (talk given at Recsys 2012)

IBM Pulse 2013 session - DevOps for Mobile Apps
IBM Pulse 2013 session - DevOps for Mobile AppsIBM Pulse 2013 session - DevOps for Mobile Apps
IBM Pulse 2013 session - DevOps for Mobile Apps
Sanjeev Sharma
 
Evaluating Php As A Technology Platform For Soa Implementations
 Evaluating Php As A Technology Platform For Soa Implementations Evaluating Php As A Technology Platform For Soa Implementations
Evaluating Php As A Technology Platform For Soa Implementations
Vedanta Barooah
 
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
mfrancis
 
Custom ERPNext Solutions
Custom ERPNext SolutionsCustom ERPNext Solutions
Custom ERPNext Solutions
Prashant Khopkar
 

Ähnlich wie From a toolkit of recommendation algorithms into a real business: the Gravity R&D experience (talk given at Recsys 2012) (20)

IBM Pulse 2013 session - DevOps for Mobile Apps
IBM Pulse 2013 session - DevOps for Mobile AppsIBM Pulse 2013 session - DevOps for Mobile Apps
IBM Pulse 2013 session - DevOps for Mobile Apps
 
Whitepaper: Volume Testing Thick Clients and Databases
Whitepaper:  Volume Testing Thick Clients and DatabasesWhitepaper:  Volume Testing Thick Clients and Databases
Whitepaper: Volume Testing Thick Clients and Databases
 
3158 - Cloud Infrastructure & It Optimization - Application Performance Manag...
3158 - Cloud Infrastructure & It Optimization - Application Performance Manag...3158 - Cloud Infrastructure & It Optimization - Application Performance Manag...
3158 - Cloud Infrastructure & It Optimization - Application Performance Manag...
 
apidays Helsinki & North 2023 - How can data-driven DevRel help identify gaps...
apidays Helsinki & North 2023 - How can data-driven DevRel help identify gaps...apidays Helsinki & North 2023 - How can data-driven DevRel help identify gaps...
apidays Helsinki & North 2023 - How can data-driven DevRel help identify gaps...
 
Evaluating Php As A Technology Platform For Soa Implementations
 Evaluating Php As A Technology Platform For Soa Implementations Evaluating Php As A Technology Platform For Soa Implementations
Evaluating Php As A Technology Platform For Soa Implementations
 
Running a World Class SaaS Organization
Running a World Class SaaS OrganizationRunning a World Class SaaS Organization
Running a World Class SaaS Organization
 
APM Talk
APM TalkAPM Talk
APM Talk
 
Marketcom PowerPoint
Marketcom PowerPointMarketcom PowerPoint
Marketcom PowerPoint
 
Meetup 2022 - API Gateway landscape.pdf
Meetup 2022 - API Gateway landscape.pdfMeetup 2022 - API Gateway landscape.pdf
Meetup 2022 - API Gateway landscape.pdf
 
Are Your Applications Delivering What Your End-Users Expect?
Are Your Applications Delivering What Your End-Users Expect?Are Your Applications Delivering What Your End-Users Expect?
Are Your Applications Delivering What Your End-Users Expect?
 
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
Keynote - The Benets of an Open Service Oriented Architecture in the Enterpr...
 
Practical guide to building public APIs
Practical guide to building public APIsPractical guide to building public APIs
Practical guide to building public APIs
 
Openly Replacing ERPs with Sugar | SugarCon 2011
Openly Replacing ERPs with Sugar | SugarCon 2011Openly Replacing ERPs with Sugar | SugarCon 2011
Openly Replacing ERPs with Sugar | SugarCon 2011
 
DevOps vs. ShadowOps (Pulse 2013)
DevOps vs. ShadowOps (Pulse 2013)DevOps vs. ShadowOps (Pulse 2013)
DevOps vs. ShadowOps (Pulse 2013)
 
Introduction to Event-Driven Architecture
Introduction to Event-Driven Architecture Introduction to Event-Driven Architecture
Introduction to Event-Driven Architecture
 
Service Management excellence with operational intelligence
Service Management excellence with operational intelligenceService Management excellence with operational intelligence
Service Management excellence with operational intelligence
 
Custom ERPNext Solutions
Custom ERPNext SolutionsCustom ERPNext Solutions
Custom ERPNext Solutions
 
Which Application Modernization Pattern Is Right For You?
Which Application Modernization Pattern Is Right For You?Which Application Modernization Pattern Is Right For You?
Which Application Modernization Pattern Is Right For You?
 
Hewlett Packard Enterprise View on Going Big with API Management - Applicatio...
Hewlett Packard Enterprise View on Going Big with API Management - Applicatio...Hewlett Packard Enterprise View on Going Big with API Management - Applicatio...
Hewlett Packard Enterprise View on Going Big with API Management - Applicatio...
 
APIs for biz dev 2.0 - Which business model?
APIs for biz dev 2.0 - Which business model?APIs for biz dev 2.0 - Which business model?
APIs for biz dev 2.0 - Which business model?
 

Mehr von Domonkos Tikk

General factorization framework for context-aware recommendations
General factorization framework for context-aware recommendationsGeneral factorization framework for context-aware recommendations
General factorization framework for context-aware recommendations
Domonkos Tikk
 
TartalomgazdagĂ­tĂĄs (content enrichment)
TartalomgazdagĂ­tĂĄs (content enrichment) TartalomgazdagĂ­tĂĄs (content enrichment)
TartalomgazdagĂ­tĂĄs (content enrichment)
Domonkos Tikk
 
Context-aware similarities within the factorization framework - presented at ...
Context-aware similarities within the factorization framework - presented at ...Context-aware similarities within the factorization framework - presented at ...
Context-aware similarities within the factorization framework - presented at ...
Domonkos Tikk
 
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
Domonkos Tikk
 
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
Domonkos Tikk
 

Mehr von Domonkos Tikk (10)

Recommenders on video sharing portals - business and algorithmic aspects
Recommenders on video sharing portals - business and algorithmic aspectsRecommenders on video sharing portals - business and algorithmic aspects
Recommenders on video sharing portals - business and algorithmic aspects
 
Neighbor methods vs matrix factorization - case studies of real-life recommen...
Neighbor methods vs matrix factorization - case studies of real-life recommen...Neighbor methods vs matrix factorization - case studies of real-life recommen...
Neighbor methods vs matrix factorization - case studies of real-life recommen...
 
General factorization framework for context-aware recommendations
General factorization framework for context-aware recommendationsGeneral factorization framework for context-aware recommendations
General factorization framework for context-aware recommendations
 
TartalomgazdagĂ­tĂĄs (content enrichment)
TartalomgazdagĂ­tĂĄs (content enrichment) TartalomgazdagĂ­tĂĄs (content enrichment)
TartalomgazdagĂ­tĂĄs (content enrichment)
 
Idomaar crowd rec_reference_fw
Idomaar crowd rec_reference_fwIdomaar crowd rec_reference_fw
Idomaar crowd rec_reference_fw
 
Big Data in Online Classifieds
Big Data in Online ClassifiedsBig Data in Online Classifieds
Big Data in Online Classifieds
 
Context-aware similarities within the factorization framework - presented at ...
Context-aware similarities within the factorization framework - presented at ...Context-aware similarities within the factorization framework - presented at ...
Context-aware similarities within the factorization framework - presented at ...
 
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
Slides from CARR 2012 WS - Enhancing Matrix Factorization Through Initializat...
 
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
Fast ALS-Based Tensor Factorization for Context-Aware Recommendation from Imp...
 
Recommender Systems Evaluation: A 3D Benchmark - presented at RUE 2012 worksh...
Recommender Systems Evaluation: A 3D Benchmark - presented at RUE 2012 worksh...Recommender Systems Evaluation: A 3D Benchmark - presented at RUE 2012 worksh...
Recommender Systems Evaluation: A 3D Benchmark - presented at RUE 2012 worksh...
 

KĂźrzlich hochgeladen

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

KĂźrzlich hochgeladen (20)

Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

From a toolkit of recommendation algorithms into a real business: the Gravity R&D experience (talk given at Recsys 2012)

  • 1. From a toolkit of recommendation algorithms into a real business: the Gravity R&D experience 13.09.2012.
  • 2. The kick-start 2 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 3. Facing with real needs What we had What clients wanted • rating prediction algorithms • recommendations that • coded in various languages bring revenue • blending mechanism • robustness • accuracy oriented • low response time • easy integration • reporting 3 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 4. What we do? users content of service provider recommender 4 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 5. Explicit vs implicit feedback No ratings but interactions sparse vs. dense matrix requires different learning 5 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 6. Increase revenue: A/B tests against the original solution internally 6 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 7. Robustness Management LAN SNMP Nagios Monitoring HP OpenView Aggregator HTTP HTTP Platform OSS/BSS / SQL / SQL IMPRESS IMPRESS SOAP Application Server #1 Application Server #2 IMPRESS Frontend web server #1 Backend LAN Reco LAN HTTP Load Balancer HTTP(S) Firewall SQL SQL CSV over FTP TV Service LAN IMPRESS Frontend web server #2 Database #1 Database #2 Reporting Subsystem End users 7 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 8. Time requirements • Response time: few ms (max 200) • Training time: maximum few hours • regular retraining • incremental training • Newsletters: • nightly batch run 8 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 9. Productization IMPRESS RECO AD•APT for for for IPTV, CATV and satellite e-commerce ad networks and ad server providers Recommends Recommends Recommends Personally Personally Relevant Relevant Personally Relevant products & services ads Linear TV, VOD, catch-up TV and more Gravity personalization platform 9 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 10. The 5% question – Importance of UI Francisco Martin (Strands): „the algorithm is only 5% in the success of the recommender system” • placement  below or above the fold  scrolling  easy to recognize  floating in • title  not misleading  explanation like • widget  carrousel  static 10 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 11. Recommendation scenario Item2Item recommendation logic: the ad’s profile will be matched to the profile model of available ads 11 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 12. Marketing channels Changing the order of two boxes: 25% CTR increase 12 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 13. Cannibalization • Goal: increase user engagement • Measurements • average visit length • average page views • Effect of accurate recommendations: • use of listing page ↓ • use of item page ↑ • Overall page view: remains the same • Secondary measurements • Contacting • CTR increase 13 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 14. Evolution: increased user engagement • not a cold start problem • parameter optimization and user engagement 14 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 15. KPIs – may change during testing 15 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 16. Complete personalization: coupon-world • Newsletter (daily + occassionally) • Ranking all offers on the website • top1 item • category preferences • user metadata (gender, age, …) • user category preferences (seldom given) • item metadata • context • customer vs. vendor 16 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 17. Business rules – driving/overriding ranking 17 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 18. Contexts 18 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 19. Context at TV program recommendation • TV (EPG program & video-on-demand)  explicit and implicit identification of the user in the household  time-dependent recommendation 19 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 20. (offline) Some results (online) Improvement using season iTALS iTALSx Dataset Recall@20 MAP@20 Recall@20 MAP@20 Grocery 64,31% 137,96% 89,99% 199,82% TV1 14,77% 43,80% 28,66% 85,33% TV2 -7,94% 10,69% 7,77% 14,15% LastFM 96,10% 116,54% 40,98% 254,62% Improvement using Seq iTALS iTALSx Dataset Recall@20 MAP@20 Recall@20 MAP@20 Grocery 84,48% 104,13% 108,83% 122,24% TV1 36,15% 55,07% 26,14% 29,93% 20 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 21. Anecdotes • Item2item recommendations – bookstore • Placebo effect • buyer vs. seller 21 From a toolkit of recommendation algorithms into a real business 13.09.2012.
  • 22. Conclusion • Offline and online testing • From simple to sophisticated • Many more potential fields of application 22 From a toolkit of recommendation algorithms into a real business 13.09.2012.