This project's goal is to analyze the interactions that users have had with articles on the IBM Watson Studio platform and make recommendations to them about new articles they might like.
This project is composed of the following steps:
-
Exploratory Data Analysis
-
Rank Based Recommendations
It consists of recommending the most popular articles simply based on the most interactions (as the articles don't have ratings). These recommendations could be made to any user (even new ones) as it doesn't take into account any other information about the user itself.
-
User-User Based Collaborative Filtering
It consists of recommending articles based on users that are similar in terms of the items they have interacted with. This is a more personalized recommendation method.
-
Matrix Factorization
This is a machine learning approach to building recommendations based on a matrix decomposition.
IBM for providing the data.
Udacity this project was developed during the Data Science Nanodegree Program.