Classification of users for ads

Project Details

The proposed system can be a general user classification mechanism that would allow us to scale app sponsorship for groups of users with similar interests. This system could be applied to the organic recommendations by the Editorial and Community teams, too. The system is partially automated, since it allows us to understand each user group qualitatively and manually manage the list of apps 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 recommendation 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.

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 Description

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