ArushiC / Recommendations-with-IBM

Make recommendations based on the interaction users have with articles on IBM Watson Studio platform

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Recommendations-with-IBM

Make recommendations based on the interaction users have with articles on IBM Watson Studio platform

Project Overview

We have user and article interaction data from IBM Watson Studio Platform. In this project, we use that data to make article recommendations for users. We have used different recommended systems like Rank based, Content based, Collaborative Filtering to make recommendations for users. Not only that, we also use SVD Matrix Factorization recommendation system and try to predict articles for unseen users.

Data Overview

The data set has 2 main datasets:

  • user-item-interactions.csv: Has user and article interactions
  • articles_community.csv: Has details about the articles

Install

This project requires Python 3.6 and the following Python libraries installed:

  • NumPy
  • Pandas
  • matplotlib
  • linalg.svd

You will also need to have software installed to run and execute a Jupyter Notebook

If you do not have Python installed yet, it is highly recommended that you install the Anaconda distribution of Python, which already has the above packages and more included. Make sure that you select Python 3.x installer.

Licensing and Acknowledgements

Thanks to Udacity for providing access to the IBM data used in this project and guidance

About

Make recommendations based on the interaction users have with articles on IBM Watson Studio platform


Languages

Language:Jupyter Notebook 62.1%Language:HTML 37.8%Language:Python 0.1%