Version 2 (modified by psantos, 2 years ago) (diff)


Classification of users for ads

Project Details

On this report, a proposal for the novel content targeting system is presented. The proposed system can be 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. The system is partially automated, since it allows us to understand each user group qualitatively and manually manage the recommendations for each group over time. Part of these recommendations can be automated based on simple rules such as app categories, trending apps within each group and most downloaded but not yet installed apps per group. It is considered that this combined marketing research/data science approach is the best solution to implement a recommender system in a very short term. The solution is also scalable and can be tweaked and improved over time. The proposed system can be constructed based on a simple three stage data mining process. The steps are described in detail from a mathematical point of view, and some technological implications are also addressed. Therefore this report can serve as the roadmap for the implementation of the system.

Purpose of this project

Project Description

Project Source Code

Source Code


Weekly Reports

Please check the Attachments section.

Trainee details

Trainee Name

Past Experience

Current Situation

Motivation for the Project


Attachments (9)