SlideShare une entreprise Scribd logo
1  sur  27
Télécharger pour lire hors ligne
Mooga App
                Personalizer	
  

                Enhancing	
  every	
  App’s	
  
                     Salability	
  


July 26, 2010
iKen’s	
  Purpose	
  and	
  Vision	
  




           Our	
  Core	
  Purpose	
  
To	
   make	
   available	
   to	
   customers	
   what	
   they	
   want.	
   Trea@ng	
   each	
   individual	
   dis@nctly	
   and	
  
Personalizing	
  his/her	
  experience	
  in	
  content/service	
  consump@on	
  lies	
  at	
  the	
  core	
  of	
  iKen’s	
  products.	
  

                Our	
  Vision	
  

We	
  are	
  poised	
  to	
  bring	
  about	
  a	
  paradigm	
  shiH	
  in	
  the	
  way	
  market	
  treats	
  customers	
  today.	
  iKen	
  is	
  
confident	
  of	
  taking	
  Mooga	
  from	
  present	
  day	
  “great	
  to	
  have”	
  percep@on	
  to	
  	
  a	
  “must	
  have”	
  demand	
  
in	
  the	
  following	
  years.	
  
iKen	
  Overview	
  

•  An	
  IIT	
  Bombay	
  research	
  spin-­‐off	
  
•  Opera@ons	
  began	
  in	
  June	
  2008	
  
•  Headcount:	
  25,	
  with	
  offices	
  in	
  Mumbai,	
  India	
  and	
  Buenos	
  Aires,	
  Argen@na	
  
•  Exper@se	
  in	
  Intelligent	
  Business	
  Systems	
  backed	
  by	
  Business	
  Intelligence	
  2.0	
  and	
  
   Hybrid	
  	
  Ar;ficial	
  Intelligence	
  Techniques	
  
•  iKen	
   has	
   a	
   comprehensive	
   soHware	
   framework	
   named	
   as	
   Mooga.	
   It	
   is	
   a	
   BI	
   2.0	
  
   pla[orm	
  for	
  N=1	
  analy@cs	
  services.	
  	
  
•  Mooga	
  can	
  be	
  applied	
  into	
  Telecom,	
  Mobile	
  VAS,	
  Internet	
  (Entertainment,	
  Retail,	
  e	
  
   Commerce),	
   Customer	
   Lifecycle	
   Management,	
   Customer	
   Care,	
   BFSI,	
   Billing,	
   ERP/
   CRM,	
   Educa@on	
   and	
   with	
   Independent	
   SoHware	
   Vendors	
   having	
   respec@ve	
  
   Domain	
  Exper@se	
  
iKen	
  References	
  
iKen’s	
  Global	
  Presence	
  –	
  Clients	
  &	
  Partners	
  




                                                 U	
  




                                                                          INDIA	
  



                                 BRAZIL	
                            SRI	
  LANKA	
  
                                                         KENYA	
  

                  PARAGUAY	
  

                ARGENTINA	
       URUGUAYY	
  
iKen	
  Recogni@ons	
  
•    NASSCOM	
  Innova@on	
  Awards	
  2008	
  Finalist	
  
•    Selected	
  by	
  MicrosoH	
  to	
  par@cipate	
  in	
  Le	
  
     Web	
  ´08	
  as	
  one	
  of	
  the	
  Top	
  10	
  innova@ve	
  
     startups	
  in	
  the	
  world.	
  
•    First	
  at	
  the	
  Tie-­‐Canaan	
  Entrepreneurial	
  
     Challenge	
  2008.	
  
•    Mooga	
  won	
  Silver	
  Award	
  for	
  “Best	
  
     Technology	
  Innova@on”	
  at	
  the	
  Mobile	
  
     Content	
  Awards	
  2008.	
  
•    Among	
  Top	
  25	
  start-­‐ups,	
  Silicon	
  India,	
  May	
  
     2010	
  hlp://www.thesmarlechie.com/magazine/	
  
•    Among	
  DARE’s	
  “75	
  start-­‐ups	
  you	
  can	
  bet	
  on”	
  
     hlp://www.dare.co.in/people/75-­‐startups-­‐you-­‐
     can-­‐bet-­‐on/iken-­‐solu@ons.htm	
  
Today’s	
  Challenges	
  

                                                    Apps	
  Apps	
  
                                                  Everywhere..!!!	
  




Operator’s	
  Dilemma	
                                                 Customer’s	
  Dilemma	
  

• Which	
  app	
  to	
  promote	
  to	
                                 • How	
  to	
  quickly	
  “get	
  
which	
  user	
                                                         navigated”	
  to	
  an	
  App	
  of	
  my	
  
• How	
  to	
  mone@ze	
  the	
  en@re	
                                choice/taste	
  
App	
  inventory	
                                                      • I	
  am	
  willing	
  to	
  pay	
  a	
  premium	
  
• How	
  to	
  enable	
  App	
  Discovery	
                             for	
  my	
  experience,	
  but	
  I	
  don’t	
  
• How	
  to	
  Personalize	
  the	
  user’s	
                           get	
  it.	
  
experience	
  
What	
  is	
  Mooga	
  
   •  Next	
   genera;on	
   personaliza;on,	
   matching,	
   discovery	
  
      and	
   recommenda;on	
   framework	
   based	
   on	
   the	
   N=1	
  
      concept	
  

   •  Supports	
   various	
   types	
   of	
   structured	
   contents	
   and	
  
      generic	
  transac;ons	
  seamlessly	
  and	
  uniformly	
  

   •  Based	
   on	
   social	
   (collabora;ve)	
   filtering,	
   content	
   (logical	
  
      and	
   contextual)	
   filtering,	
   intelligent	
   matching	
   and	
   on	
  
      individual	
   tastes	
   along	
   with	
   adapta;on	
   to	
   ;me	
   and	
  
      loca;on	
  dimensions	
  

   •  Works	
   in	
   real-­‐;me,	
   self-­‐learning	
   and	
   is	
   completely	
  
      programmable,	
   configurable	
   and	
   customizable	
   based	
   on	
  
      products,	
  contents	
  and	
  required	
  func;onality	
  
Mooga	
  Hybrid	
  AI	
  Framework	
  
                               Understanding
                                 wisdom of
                                crowd (what
                                people do?)

                                                   Content filtering
          Adapting to                               and clustering
      changing personal
             tastes
        (including time
        and location )             Mooga
                               Hybrid Artificial
                                Intelligence
                                Framework
                                                       Business rules,
                                                      Flexible modeling,
            Intelligent User                          configuration and
           Criteria Matching                            customization


                                  Lazy learning,
                                  adaptive and
                                    real-time
                                   framework
Mooga	
  App	
  Personalizer	
  (MAP)	
  
                                                           Personal	
  
                                                          Preferences	
     Business	
  
                                       Wisdom	
  of	
  
                                                                            Rules	
  &	
  
                                        Crowd	
  
                                                                            Policies	
  

                    Dynamic	
  
                                                                                             Personal	
  
                   Behavior	
  &	
  
                                                                                              Profile	
  
                   Interac@on	
  



                App	
                                      Inputs	
                                Market	
  
              Metadata	
  
                                                          to	
  MAP	
                           Informa@on	
  



   Mooga	
   Analy@cs	
   Engine	
   learns	
  
   each	
   user’s	
   taste	
   &	
   preference	
  
   thru	
  her	
  consump@on	
  palern	
  and	
  
   picks	
   up	
   the	
   most	
   relevant	
   app	
  
   that	
  suits	
  her	
  liking	
  

                              Personalized	
  Apps	
  to	
  every	
  user	
  	
  
Why	
  Mooga	
  App	
  Personalizer	
  
How	
  does	
  it	
  work?	
  
                       INPUT	
                               P&R	
  Processing	
                            OUTPUT	
  (N=1)	
  
 User Transactions                 User Profile
                                                         Users’ Transactions,
                                                          Ratings, Tagging,
                                                                    	
  
                                                                 etc.
 Buy, browse,                           Personal
 download, referred                Attributes(global
 Ratings and location                  and local)             Clustering                                          Individualized and
                                                                                     Meta Contents,
                                                          (based on feature                                       Common contents
                                                              matching)	
  
                                                                                      Taxonomy,
                                                                                      Keywords,
                                                           Content Filtering	
          Tags,…	
  
     User
     Preferences	
                                           Dynamic and               Domain
                                                                         	
  
                                                           Incremental CFs            Knowledge	
  
                                                                                                         Products or contents or promotional
                                                                          	
  
                                                          Content Discovery                              material or advertisements (at what
  User Profile Data                                                                   User and           time
  What kind of products or contents user likes?          True personalization      Business Logic        and when) the customer/user will
  What keywords, tags, etc. user searches?                based on Hybrid AI	
                    	
  
                                                                                   and Policy Rules      likely
  What campaigns user responds?                                                                          respond to or would like to buy/view/
                                                            Basic Ranked                                 download or should be served.
  When user prefers transactions (day, time,                 DB Search 	
              Content
  month)?                                                                              Universe	
        Automatically
  Where user does transaction (location)?                      Hybrid AI                                 skips the contents already
  What kind of likely personal characteristics user is       Techniques 	
                               downloaded/bought etc. 	
  
  having?
Example-­‐Clustering	
  based	
  on	
  N=1	
  
                       N=G	
              N=LT	
             N=1	
  




      Customers	
     Broader	
           Long	
  Tail	
      Unique	
  and	
  
                      Groups	
            (niches)	
          personalized	
  
                      (Clustering/	
                          experiences	
  
                      Classifica@on)	
  
Create	
  Unlimited	
  Cluster	
  Types	
  

 Heavy Users                                 Cluster can be created based
                                             upon different Parameters
                                             •  Usage (Heavy, Moderate, etc)

                                             •  Location

                                             •  Access Interface (Web/WAP etc)

                                             •  Content Category
                           WEB(interface
                           based cluster)
                                             •  Demographics
IVR(interface
 based cluster)                              •  Other configurable cluster

                        Enthusiastic users   •  Combinations of defined clusters

  Common between two Clusters
All	
  this	
  Results	
  in	
  

                        Operator’s	
  Delight	
  

                        • User	
  specific	
  Personalized	
  App	
  promo@on	
  
                        • Mone@za@on	
  of	
  Long	
  Tail	
  thru	
  Discovery	
  
                        • Increased	
  Customer	
  S@ckiness	
  	
  
                        • More	
  revenue	
  from	
  each	
  user	
  




                        Customer’s	
  Delight	
  

                        • Superior	
  Experience	
  
                        • Less	
  pain	
  in	
  naviga@on	
  
                        • “I	
  get	
  what	
  I	
  want”	
  	
  
Exploit	
  the	
  Unexploited	
  	
  
P&R	
  Logical	
  level	
  diagram	
  
Mooga	
  Component	
  Level	
  Architecture	
  
               Application                               Application                             Application        Application
               Front-end                                 Front-end                               Front-end          Front-end
                (Mobile)                                   (Web)                                (Broadband         (Digital TV)
                                                                                                      )


                                 Client Application Server (Web/WAP/IVR, etc Server)

                                          Integration APIs to wrap web services

                                       User	
  info	
  &	
                          P&R	
  
                                       Click	
  Streams                             Information                      Domain	
  
                                                                                                                    Vocabulary	
  	
  


                  iKen	
  Studio	
                  Mooga	
  P&R	
                    Scheduler	
  
                                                                                                               Application	
  speciEic	
  
                                                    extensions	
  
                                                       Web	
  Services	
                                          Vocabulary	
  


                                                                                                                Domain	
  logic	
  and	
  
            Meta	
  data	
                                                                                      models:	
  Business	
  
            creation	
  and	
  data	
                                                                            Rules,	
  logic	
  etc.	
  
            synchronization

                                                                             Mooga	
  P&R	
  
                  Tag	
  Mapping	
                                            Database	
  




      CMS DB/Content DB/RSS Feeds
Case	
  Study:	
  Airtel	
  
About	
  Airtel	
  
•    Bhar@	
   Airtel	
   Limited,	
   formerly	
   known	
   as	
   Bhar@	
   Tele-­‐Ventures	
   LTD	
   (BTVL)	
   is	
   an	
  
     Indian	
  company	
  offering	
  tele-­‐communica@on	
  services	
  in	
  18	
  countries.	
  	
  
•    It	
   the	
   largest	
   cellular	
   service	
   provider	
   in	
   India,	
   with	
   more	
   than	
   135	
   million	
  
     subscrip@ons	
  as	
  of	
  May	
  2010.	
  	
  
•    Bhar@	
   Airtel	
   is	
   the	
   world's	
   third	
   largest,	
   single-­‐country	
   mobile	
   operator	
   and	
   fiHh	
  
     largest	
   telecom	
   operator	
   in	
   the	
   world	
   in	
   terms	
   of	
   subscriber	
   base.	
   It	
   also	
   offers	
  
     fixed	
  line	
  services	
  and	
  broadband	
  services.	
  	
  
•    It	
  offers	
  its	
  telecom	
  services	
  under	
  the	
  Airtel	
  brand	
  


POC	
  for	
  Personalized	
  Ring	
  Back	
  Tones(RBT):	
  Scope	
  
•    Aitel	
  proposed	
  a	
  market	
  with	
  high-­‐traffic,	
  diverse	
  demographics,	
  high	
  consump@on	
  
     of	
   music	
   and	
   which	
   could	
   be	
   representa@ve	
   for	
   other	
   markets.	
   Mumbai	
   was	
   the	
  
     chosen	
  circle.	
  
•    RBTs	
   get	
   downloaded	
   through	
   various	
   channels	
   such	
   as	
   WAP,	
   USSD,	
   IVR,	
   *Copy,	
  
     OBD,	
   etc.	
   Implemen@ng	
   Mooga	
   services	
   on	
   a	
   Virtual	
   Number	
   (VN)	
   was	
   step	
   1.	
  
     Based	
  on	
  results,	
  integra@on	
  on	
  other	
  channels	
  was	
  to	
  be	
  encompassed.	
  A	
  virtual	
  
     number	
   is	
   a	
   short/long	
   code	
   which	
   subscribers	
   dial	
   in	
   to	
   listen	
   to	
   a	
   sequence	
   of	
  
     songs.	
  They	
  can	
  select	
  a	
  song	
  of	
  their	
  choice	
  any@me	
  by	
  pressing	
  a	
  *.	
  
Case	
  Study:	
  Airtel	
  
POC	
  for	
  Personalized	
  RBTs:	
  Scope	
  

•    Before	
  Mooga	
  deployment,	
  Airtel	
  would	
  play	
  a	
  set	
  of	
  5	
  songs	
  randomly	
  every	
  day	
  
     for	
  all	
  its	
  subscribers	
  (irrespec@ve	
  of	
  their	
  likings).	
  If	
  a	
  user	
  didn’t	
  find	
  a	
  song	
  of	
  her	
  
     interest	
  aHer	
  calling	
  the	
  VN,	
  she	
  would	
  hang	
  up	
  and	
  call	
  back	
  aHer	
  some	
  @me	
  to	
  
     get	
   to	
   listen	
   to	
   a	
   new	
   set	
   of	
   songs.	
   This	
   would	
   go	
   on	
   @ll	
   she	
   would	
   finally	
   come	
  
     across	
  a	
  song	
  of	
  her	
  choice.	
  	
  
•    We	
  started	
  off	
  with	
  providing	
  Personalized	
  Recommenda@ons	
  on	
  the	
  VN	
  from	
  the	
  
     1st	
   week	
   of	
   June	
   2010.	
   Mooga	
   gave	
   Personalized	
   Recommenda@ons	
   to	
   each	
   and	
  
     every	
   individual	
   based	
   on	
   her	
   taste	
   and	
   liking.	
   The	
   sequence	
   of	
   songs	
   would	
  
     dynamically	
  change	
  in	
  real-­‐@me	
  from	
  session	
  to	
  session.	
  
•    Since	
   Mooga	
   is	
   a	
   self-­‐learning	
   system,	
   Recommenda@ons	
   get	
   more	
   and	
   more	
  
     precise	
  and	
  relevant	
  with	
  @me	
  (as	
  the	
  system	
  learns	
  more	
  about	
  the	
  user).	
  
Case	
  Study:	
  Airtel	
  
 Results	
  
   The	
  average	
  number	
  of	
  downloads	
  increased	
  by	
  a	
  staggering	
  150%	
  over	
  the	
  VN	
  in	
  
    just	
  a	
  span	
  of	
  1	
  month.	
  
   From	
  a	
  Sales	
  Distribu@on	
  perspec@ve,	
  Mooga	
  is	
  helping	
  Airtel	
  sell	
  in	
  one	
  day	
  what	
  
    they	
  used	
  to	
  sell	
  in	
  one	
  month.	
  
   The	
  total	
  numbers	
  of	
  calls	
  made	
  to	
  the	
  VN	
  have	
  increased	
  thrice	
  as	
  much	
  as	
  people	
  
    are	
   making	
   more	
   and	
   more	
   calls	
   as	
   they	
   are	
   hearing	
   up	
   to	
   100	
   songs	
   of	
   their	
  
    interest	
  from	
  earlier	
  5	
  earlier.	
  Because	
  it	
  is	
  a	
  toll	
  free	
  number,	
  people	
  have	
  made	
  
    this	
  like	
  radio.	
  Here	
  conversion	
  rate	
  is	
  higher	
  than	
  10%	
  	
  	
  
Contact	
  Details	
  


  India                                   Latin America

  iKen Solutions India Pvt. Ltd.          iKen Solutions – Americas
  3rd Floor, SINE, CSRE Department        Blanco Encalada 88, Piso 1, Oficina 6,
                                          Boulogne
  Indian Institute of Technology Bombay
                                          (CP 1609) Buenos Aires, Argentina
  Powai, Mumbai - 400 076, India
                                          Email: iKen@iKensolutions.com
  Phone1: +91-22-2572 2675
  Phone2: +91-22-6518 2059
  Email: iKen@iKensolutions.com
www.ikensolu@ons.com	
  

Thank	
  You	
  

Contenu connexe

Similaire à Mooga app personalizer

Collaborative Lifecycle Managmenent - an Introduction
Collaborative Lifecycle Managmenent - an IntroductionCollaborative Lifecycle Managmenent - an Introduction
Collaborative Lifecycle Managmenent - an IntroductionStrongback Consulting
 
Timelytrendsin appdelivery
Timelytrendsin appdeliveryTimelytrendsin appdelivery
Timelytrendsin appdeliveryKelly Emo
 
Kratin Mpid Overview
Kratin Mpid OverviewKratin Mpid Overview
Kratin Mpid OverviewSatin Katiyar
 
Cloud Limitless 2012
Cloud Limitless 2012Cloud Limitless 2012
Cloud Limitless 2012apsheehan
 
IBM Social Portal 2012 (Korean)
IBM Social Portal 2012 (Korean)IBM Social Portal 2012 (Korean)
IBM Social Portal 2012 (Korean)Do Hyun Kim
 
Product portfolio 2011
Product portfolio   2011Product portfolio   2011
Product portfolio 2011David Wolfe
 
Future of retail retail social business architektur 2012
Future of retail  retail social business architektur 2012Future of retail  retail social business architektur 2012
Future of retail retail social business architektur 2012Friedel Jonker
 
Multi channel strategy mo mo chicago jan 24 final
Multi channel strategy mo mo chicago jan 24 finalMulti channel strategy mo mo chicago jan 24 final
Multi channel strategy mo mo chicago jan 24 finalNiti Vaish
 
iPath enterprise mobilization technology and solutions overview
iPath enterprise mobilization technology and solutions overviewiPath enterprise mobilization technology and solutions overview
iPath enterprise mobilization technology and solutions overviewiPathTech
 
The Essentials of Great Search Design (ECIR 2010)
The Essentials of Great Search Design (ECIR 2010)The Essentials of Great Search Design (ECIR 2010)
The Essentials of Great Search Design (ECIR 2010)Vegard Sandvold
 
Using Mobile as an Instrument to Affect Behavior
Using Mobile as an Instrument to Affect BehaviorUsing Mobile as an Instrument to Affect Behavior
Using Mobile as an Instrument to Affect BehaviorPhil Hendrix
 
Iotx futures research_futures_trends_2011
Iotx futures research_futures_trends_2011Iotx futures research_futures_trends_2011
Iotx futures research_futures_trends_2011Andy Hunter
 
Making Sense of Lean Startup Strategies
Making Sense of Lean Startup StrategiesMaking Sense of Lean Startup Strategies
Making Sense of Lean Startup StrategiesSathish Hariharan
 
"Everything is a service" (Redux)
"Everything is a service" (Redux)"Everything is a service" (Redux)
"Everything is a service" (Redux)Sylvain Cottong
 
Business intelligence for n=1 analytics using hybrid intelligent system approach
Business intelligence for n=1 analytics using hybrid intelligent system approachBusiness intelligence for n=1 analytics using hybrid intelligent system approach
Business intelligence for n=1 analytics using hybrid intelligent system approachiken Solutions - Web Space-
 
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint IntranetCuneyt Uysal
 

Similaire à Mooga app personalizer (20)

Collaborative Lifecycle Managmenent - an Introduction
Collaborative Lifecycle Managmenent - an IntroductionCollaborative Lifecycle Managmenent - an Introduction
Collaborative Lifecycle Managmenent - an Introduction
 
Timelytrendsin appdelivery
Timelytrendsin appdeliveryTimelytrendsin appdelivery
Timelytrendsin appdelivery
 
User Experience 2: Talk@Stabilo
User Experience 2: Talk@StabiloUser Experience 2: Talk@Stabilo
User Experience 2: Talk@Stabilo
 
Kratin Mpid Overview
Kratin Mpid OverviewKratin Mpid Overview
Kratin Mpid Overview
 
Cloud Limitless 2012
Cloud Limitless 2012Cloud Limitless 2012
Cloud Limitless 2012
 
GirnarSoft Profile
GirnarSoft ProfileGirnarSoft Profile
GirnarSoft Profile
 
IBM Social Portal 2012 (Korean)
IBM Social Portal 2012 (Korean)IBM Social Portal 2012 (Korean)
IBM Social Portal 2012 (Korean)
 
GirnarSoft Profile
GirnarSoft ProfileGirnarSoft Profile
GirnarSoft Profile
 
GirnarSoft Profile
GirnarSoft ProfileGirnarSoft Profile
GirnarSoft Profile
 
Product portfolio 2011
Product portfolio   2011Product portfolio   2011
Product portfolio 2011
 
Future of retail retail social business architektur 2012
Future of retail  retail social business architektur 2012Future of retail  retail social business architektur 2012
Future of retail retail social business architektur 2012
 
Multi channel strategy mo mo chicago jan 24 final
Multi channel strategy mo mo chicago jan 24 finalMulti channel strategy mo mo chicago jan 24 final
Multi channel strategy mo mo chicago jan 24 final
 
iPath enterprise mobilization technology and solutions overview
iPath enterprise mobilization technology and solutions overviewiPath enterprise mobilization technology and solutions overview
iPath enterprise mobilization technology and solutions overview
 
The Essentials of Great Search Design (ECIR 2010)
The Essentials of Great Search Design (ECIR 2010)The Essentials of Great Search Design (ECIR 2010)
The Essentials of Great Search Design (ECIR 2010)
 
Using Mobile as an Instrument to Affect Behavior
Using Mobile as an Instrument to Affect BehaviorUsing Mobile as an Instrument to Affect Behavior
Using Mobile as an Instrument to Affect Behavior
 
Iotx futures research_futures_trends_2011
Iotx futures research_futures_trends_2011Iotx futures research_futures_trends_2011
Iotx futures research_futures_trends_2011
 
Making Sense of Lean Startup Strategies
Making Sense of Lean Startup StrategiesMaking Sense of Lean Startup Strategies
Making Sense of Lean Startup Strategies
 
"Everything is a service" (Redux)
"Everything is a service" (Redux)"Everything is a service" (Redux)
"Everything is a service" (Redux)
 
Business intelligence for n=1 analytics using hybrid intelligent system approach
Business intelligence for n=1 analytics using hybrid intelligent system approachBusiness intelligence for n=1 analytics using hybrid intelligent system approach
Business intelligence for n=1 analytics using hybrid intelligent system approach
 
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet
2011 newsgator Cuneyt Uysal 6 Steps to Social SharePoint Intranet
 

Plus de iken Solutions - Web Space-

MOOGA: Next generation BI a knowledge based approach using intelligent systems
MOOGA: Next generation BI a knowledge based approach using intelligent systemsMOOGA: Next generation BI a knowledge based approach using intelligent systems
MOOGA: Next generation BI a knowledge based approach using intelligent systemsiken Solutions - Web Space-
 
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009iken Solutions - Web Space-
 

Plus de iken Solutions - Web Space- (20)

MOOGA: Next generation BI a knowledge based approach using intelligent systems
MOOGA: Next generation BI a knowledge based approach using intelligent systemsMOOGA: Next generation BI a knowledge based approach using intelligent systems
MOOGA: Next generation BI a knowledge based approach using intelligent systems
 
Palermo Valley - Mobile Sessions
Palermo Valley - Mobile SessionsPalermo Valley - Mobile Sessions
Palermo Valley - Mobile Sessions
 
Mooga Sony Music Case study (Update April. 09)
Mooga Sony Music Case study (Update April. 09)Mooga Sony Music Case study (Update April. 09)
Mooga Sony Music Case study (Update April. 09)
 
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009
Mobile Marketing Forum : LATAM (São Paulo) - March 24 - 26, 2009
 
Mooga - Entendiendo al usuario
Mooga - Entendiendo al usuarioMooga - Entendiendo al usuario
Mooga - Entendiendo al usuario
 
Mooga Sonybmg Case study (Update Nov. 08)
Mooga  Sonybmg Case study (Update Nov. 08)Mooga  Sonybmg Case study (Update Nov. 08)
Mooga Sonybmg Case study (Update Nov. 08)
 
Convergence 2
Convergence 2Convergence 2
Convergence 2
 
Presentación Palermo Valley
Presentación Palermo ValleyPresentación Palermo Valley
Presentación Palermo Valley
 
Mobile Operators the new supermarkets
Mobile Operators the new supermarketsMobile Operators the new supermarkets
Mobile Operators the new supermarkets
 
Mobile Search Vs Mobile Discovery
Mobile Search Vs Mobile DiscoveryMobile Search Vs Mobile Discovery
Mobile Search Vs Mobile Discovery
 
A new King has rise "The mobile phone"
A new King has rise "The mobile phone"A new King has rise "The mobile phone"
A new King has rise "The mobile phone"
 
Mobile Marketing Forum - MOOGA
Mobile Marketing Forum - MOOGAMobile Marketing Forum - MOOGA
Mobile Marketing Forum - MOOGA
 
Mooga iSearch
Mooga iSearchMooga iSearch
Mooga iSearch
 
Mooga Ivas
Mooga IvasMooga Ivas
Mooga Ivas
 
Mooga Longtail
Mooga LongtailMooga Longtail
Mooga Longtail
 
Mobilesupermarkets
MobilesupermarketsMobilesupermarkets
Mobilesupermarkets
 
Mooga - Concept !!
Mooga - Concept !!Mooga - Concept !!
Mooga - Concept !!
 
Tie canaan final 2008
Tie canaan final 2008Tie canaan final 2008
Tie canaan final 2008
 
Ikenstudio Brochure
Ikenstudio BrochureIkenstudio Brochure
Ikenstudio Brochure
 
Hybrid Intelligent Systems
Hybrid Intelligent SystemsHybrid Intelligent Systems
Hybrid Intelligent Systems
 

Dernier

CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
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
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 

Dernier (20)

CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
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
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 

Mooga app personalizer

  • 1. Mooga App Personalizer   Enhancing  every  App’s   Salability   July 26, 2010
  • 2.
  • 3. iKen’s  Purpose  and  Vision   Our  Core  Purpose   To   make   available   to   customers   what   they   want.   Trea@ng   each   individual   dis@nctly   and   Personalizing  his/her  experience  in  content/service  consump@on  lies  at  the  core  of  iKen’s  products.   Our  Vision   We  are  poised  to  bring  about  a  paradigm  shiH  in  the  way  market  treats  customers  today.  iKen  is   confident  of  taking  Mooga  from  present  day  “great  to  have”  percep@on  to    a  “must  have”  demand   in  the  following  years.  
  • 4. iKen  Overview   •  An  IIT  Bombay  research  spin-­‐off   •  Opera@ons  began  in  June  2008   •  Headcount:  25,  with  offices  in  Mumbai,  India  and  Buenos  Aires,  Argen@na   •  Exper@se  in  Intelligent  Business  Systems  backed  by  Business  Intelligence  2.0  and   Hybrid    Ar;ficial  Intelligence  Techniques   •  iKen   has   a   comprehensive   soHware   framework   named   as   Mooga.   It   is   a   BI   2.0   pla[orm  for  N=1  analy@cs  services.     •  Mooga  can  be  applied  into  Telecom,  Mobile  VAS,  Internet  (Entertainment,  Retail,  e   Commerce),   Customer   Lifecycle   Management,   Customer   Care,   BFSI,   Billing,   ERP/ CRM,   Educa@on   and   with   Independent   SoHware   Vendors   having   respec@ve   Domain  Exper@se  
  • 6. iKen’s  Global  Presence  –  Clients  &  Partners   U   INDIA   BRAZIL   SRI  LANKA   KENYA   PARAGUAY   ARGENTINA   URUGUAYY  
  • 7. iKen  Recogni@ons   •  NASSCOM  Innova@on  Awards  2008  Finalist   •  Selected  by  MicrosoH  to  par@cipate  in  Le   Web  ´08  as  one  of  the  Top  10  innova@ve   startups  in  the  world.   •  First  at  the  Tie-­‐Canaan  Entrepreneurial   Challenge  2008.   •  Mooga  won  Silver  Award  for  “Best   Technology  Innova@on”  at  the  Mobile   Content  Awards  2008.   •  Among  Top  25  start-­‐ups,  Silicon  India,  May   2010  hlp://www.thesmarlechie.com/magazine/   •  Among  DARE’s  “75  start-­‐ups  you  can  bet  on”   hlp://www.dare.co.in/people/75-­‐startups-­‐you-­‐ can-­‐bet-­‐on/iken-­‐solu@ons.htm  
  • 8.
  • 9. Today’s  Challenges   Apps  Apps   Everywhere..!!!   Operator’s  Dilemma   Customer’s  Dilemma   • Which  app  to  promote  to   • How  to  quickly  “get   which  user   navigated”  to  an  App  of  my   • How  to  mone@ze  the  en@re   choice/taste   App  inventory   • I  am  willing  to  pay  a  premium   • How  to  enable  App  Discovery   for  my  experience,  but  I  don’t   • How  to  Personalize  the  user’s   get  it.   experience  
  • 10. What  is  Mooga   •  Next   genera;on   personaliza;on,   matching,   discovery   and   recommenda;on   framework   based   on   the   N=1   concept   •  Supports   various   types   of   structured   contents   and   generic  transac;ons  seamlessly  and  uniformly   •  Based   on   social   (collabora;ve)   filtering,   content   (logical   and   contextual)   filtering,   intelligent   matching   and   on   individual   tastes   along   with   adapta;on   to   ;me   and   loca;on  dimensions   •  Works   in   real-­‐;me,   self-­‐learning   and   is   completely   programmable,   configurable   and   customizable   based   on   products,  contents  and  required  func;onality  
  • 11. Mooga  Hybrid  AI  Framework   Understanding wisdom of crowd (what people do?) Content filtering Adapting to and clustering changing personal tastes (including time and location ) Mooga Hybrid Artificial Intelligence Framework Business rules, Flexible modeling, Intelligent User configuration and Criteria Matching customization Lazy learning, adaptive and real-time framework
  • 12. Mooga  App  Personalizer  (MAP)   Personal   Preferences   Business   Wisdom  of   Rules  &   Crowd   Policies   Dynamic   Personal   Behavior  &   Profile   Interac@on   App   Inputs   Market   Metadata   to  MAP   Informa@on   Mooga   Analy@cs   Engine   learns   each   user’s   taste   &   preference   thru  her  consump@on  palern  and   picks   up   the   most   relevant   app   that  suits  her  liking   Personalized  Apps  to  every  user    
  • 13. Why  Mooga  App  Personalizer  
  • 14. How  does  it  work?   INPUT   P&R  Processing   OUTPUT  (N=1)   User Transactions User Profile Users’ Transactions, Ratings, Tagging,   etc. Buy, browse, Personal download, referred Attributes(global Ratings and location and local) Clustering Individualized and Meta Contents, (based on feature Common contents matching)   Taxonomy, Keywords, Content Filtering   Tags,…   User Preferences   Dynamic and Domain   Incremental CFs Knowledge   Products or contents or promotional   Content Discovery material or advertisements (at what User Profile Data User and time What kind of products or contents user likes? True personalization Business Logic and when) the customer/user will What keywords, tags, etc. user searches? based on Hybrid AI     and Policy Rules likely What campaigns user responds? respond to or would like to buy/view/ Basic Ranked download or should be served. When user prefers transactions (day, time, DB Search   Content month)? Universe   Automatically Where user does transaction (location)? Hybrid AI skips the contents already What kind of likely personal characteristics user is Techniques   downloaded/bought etc.   having?
  • 15. Example-­‐Clustering  based  on  N=1   N=G   N=LT   N=1   Customers   Broader   Long  Tail   Unique  and   Groups   (niches)   personalized   (Clustering/   experiences   Classifica@on)  
  • 16. Create  Unlimited  Cluster  Types   Heavy Users Cluster can be created based upon different Parameters •  Usage (Heavy, Moderate, etc) •  Location •  Access Interface (Web/WAP etc) •  Content Category WEB(interface based cluster) •  Demographics IVR(interface based cluster) •  Other configurable cluster Enthusiastic users •  Combinations of defined clusters Common between two Clusters
  • 17. All  this  Results  in   Operator’s  Delight   • User  specific  Personalized  App  promo@on   • Mone@za@on  of  Long  Tail  thru  Discovery   • Increased  Customer  S@ckiness     • More  revenue  from  each  user   Customer’s  Delight   • Superior  Experience   • Less  pain  in  naviga@on   • “I  get  what  I  want”    
  • 19.
  • 20. P&R  Logical  level  diagram  
  • 21. Mooga  Component  Level  Architecture   Application Application Application Application Front-end Front-end Front-end Front-end (Mobile) (Web) (Broadband (Digital TV) ) Client Application Server (Web/WAP/IVR, etc Server) Integration APIs to wrap web services User  info  &   P&R   Click  Streams Information Domain   Vocabulary     iKen  Studio   Mooga  P&R   Scheduler   Application  speciEic   extensions   Web  Services   Vocabulary   Domain  logic  and   Meta  data   models:  Business   creation  and  data   Rules,  logic  etc.   synchronization Mooga  P&R   Tag  Mapping   Database   CMS DB/Content DB/RSS Feeds
  • 22.
  • 23. Case  Study:  Airtel   About  Airtel   •  Bhar@   Airtel   Limited,   formerly   known   as   Bhar@   Tele-­‐Ventures   LTD   (BTVL)   is   an   Indian  company  offering  tele-­‐communica@on  services  in  18  countries.     •  It   the   largest   cellular   service   provider   in   India,   with   more   than   135   million   subscrip@ons  as  of  May  2010.     •  Bhar@   Airtel   is   the   world's   third   largest,   single-­‐country   mobile   operator   and   fiHh   largest   telecom   operator   in   the   world   in   terms   of   subscriber   base.   It   also   offers   fixed  line  services  and  broadband  services.     •  It  offers  its  telecom  services  under  the  Airtel  brand   POC  for  Personalized  Ring  Back  Tones(RBT):  Scope   •  Aitel  proposed  a  market  with  high-­‐traffic,  diverse  demographics,  high  consump@on   of   music   and   which   could   be   representa@ve   for   other   markets.   Mumbai   was   the   chosen  circle.   •  RBTs   get   downloaded   through   various   channels   such   as   WAP,   USSD,   IVR,   *Copy,   OBD,   etc.   Implemen@ng   Mooga   services   on   a   Virtual   Number   (VN)   was   step   1.   Based  on  results,  integra@on  on  other  channels  was  to  be  encompassed.  A  virtual   number   is   a   short/long   code   which   subscribers   dial   in   to   listen   to   a   sequence   of   songs.  They  can  select  a  song  of  their  choice  any@me  by  pressing  a  *.  
  • 24. Case  Study:  Airtel   POC  for  Personalized  RBTs:  Scope   •  Before  Mooga  deployment,  Airtel  would  play  a  set  of  5  songs  randomly  every  day   for  all  its  subscribers  (irrespec@ve  of  their  likings).  If  a  user  didn’t  find  a  song  of  her   interest  aHer  calling  the  VN,  she  would  hang  up  and  call  back  aHer  some  @me  to   get   to   listen   to   a   new   set   of   songs.   This   would   go   on   @ll   she   would   finally   come   across  a  song  of  her  choice.     •  We  started  off  with  providing  Personalized  Recommenda@ons  on  the  VN  from  the   1st   week   of   June   2010.   Mooga   gave   Personalized   Recommenda@ons   to   each   and   every   individual   based   on   her   taste   and   liking.   The   sequence   of   songs   would   dynamically  change  in  real-­‐@me  from  session  to  session.   •  Since   Mooga   is   a   self-­‐learning   system,   Recommenda@ons   get   more   and   more   precise  and  relevant  with  @me  (as  the  system  learns  more  about  the  user).  
  • 25. Case  Study:  Airtel   Results     The  average  number  of  downloads  increased  by  a  staggering  150%  over  the  VN  in   just  a  span  of  1  month.     From  a  Sales  Distribu@on  perspec@ve,  Mooga  is  helping  Airtel  sell  in  one  day  what   they  used  to  sell  in  one  month.     The  total  numbers  of  calls  made  to  the  VN  have  increased  thrice  as  much  as  people   are   making   more   and   more   calls   as   they   are   hearing   up   to   100   songs   of   their   interest  from  earlier  5  earlier.  Because  it  is  a  toll  free  number,  people  have  made   this  like  radio.  Here  conversion  rate  is  higher  than  10%      
  • 26. Contact  Details   India Latin America iKen Solutions India Pvt. Ltd. iKen Solutions – Americas 3rd Floor, SINE, CSRE Department Blanco Encalada 88, Piso 1, Oficina 6, Boulogne Indian Institute of Technology Bombay (CP 1609) Buenos Aires, Argentina Powai, Mumbai - 400 076, India Email: iKen@iKensolutions.com Phone1: +91-22-2572 2675 Phone2: +91-22-6518 2059 Email: iKen@iKensolutions.com