wiki:ClassificationOfUsersForAds

Version 7 (modified by psantos, 3 years ago) (diff)

--

Classification of users for ads

Purpose of this project

Create a general user classification mechanism that would allow us to scale app recommendations for groups of users with similar interests. This system could be applied to the organic recommendations by the Editorial and Community teams, but also to the Advertising/Monetisation? processes.

Project Details

Develop a user classification mechanism that will allow us to scale app sponsorship and app recommendations for groups of users with similar interests. This process will have consist in four phases:
1.Identify Most Important Targets

-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.
2.Build Predictive Algorithm

-A very simple and computationally cheap algorithm (K-Nearest Neighbors) can be applied on the entire Hadoop Data lake.
3.Implement UI Interface Filter per Target

4.Plan Content Targeting for Each Group Based on General App Categories.

Project Source Code

Source Code

Road-map

July 21st - Multidimensional Scaling done

July 28th - Hierarchichal Clustering done

Weekly Reports

Please check the Attachments section.

Trainee details

Trainee Name

Pedro Miguel Matias Santos

Past Experience

Academic only

Current Situation

Summer Intern

Motivation for the Project

I am very motivated because I'm planning to take a master in Intelligent Systems and Bid Data.

Mentor

Luis Pinto;

Pedro Santos

Attachments (9)