Changes between Version 6 and Version 7 of ClassificationOfUsersForAds


Ignore:
Timestamp:
Jul 22, 2017, 1:05:57 AM (2 years ago)
Author:
psantos
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • ClassificationOfUsersForAds

    v6 v7  
    1212mechanism that will allow us to scale app sponsorship and app recommendations for
    1313groups of users with similar interests. This process will have consist in four phases: [[BR]]
    14 {{{1.Identify Most Important Targets
    15 {{{This will be achieved by using a combined marketing research/data mining approach. First, gather a sample of users, with all the apps installed per user. Multidimensional Scaling + Clustering can be applied on the sample. The clustering results need to be interpreted using brainstorming sessions with multidisciplinary teams, to construct realistic and rich profiles.}}} }}}[[BR]]
    16 {{{2.Build Predictive Algorithm
    17 {{{A very simple and computationally cheap algorithm (K-Nearest Neighbors) can be applied on the entire Hadoop Data lake.}}} }}}
     141.Identify Most Important Targets[[BR]]
    1815
    19 {{{3.Implement UI Interface Filter per Target}}}
    20 {{{4.Plan Content Targeting for Each Group Based on General App Categories.}}}
     16-This will be achieved by using a combined marketing research/data mining approach. First, gather a sample of users, with all the apps installed per user. Multidimensional Scaling + Clustering can be applied on the sample. The clustering results need to be interpreted using brainstorming sessions with multidisciplinary teams, to construct realistic and rich profiles.[[BR]]
     172.Build Predictive Algorithm[[BR]]
     18
     19-A very simple and computationally cheap algorithm (K-Nearest Neighbors) can be applied on the entire Hadoop Data lake.[[BR]]
     203.Implement UI Interface Filter per Target[[BR]]
     21
     224.Plan Content Targeting for Each Group Based on General App Categories.
    2123
    2224