This is an inclass competition for students at FEUP - MIEGI taking Estatística Mulivariada. 
Detailed assignment instructions are given in the [course Moodle page](https://moodle.up.pt/course/view.php?id=1948).

In this competition your task is to predict the articles'  number of shares in social media. The data comes from website mashable.com from beginning of 2015. The dataset used in the competition can be found at the [UCI repository](https://archive.ics.uci.edu/ml/datasets/Online+News+Popularity#). Please note, the articles number of shares have been randomly changed to prevent cheating.

There is a public leaderboard which is computed on about 30% of the test data and a private one that is computed on the remaining observations. You can use the public leaderboard to evaluate your current standing till the deadline date. The final rankings will be based on the private leaderboard. Bear in mind that by submitting many times to the public leaderboard and making decisions upon these results you might **overfit your model**.

**Acknowledgments**

The dataset used in the competition can be found at the UCI repository. We thank Kelwin Fernandes, Pedro Vinagre, Paulo Cortez and Pedro Sernadela for making it publicly available. Check also their publication below.
K. Fernandes, P. Vinagre and P. Cortez. A Proactive Intelligent Decision Support System for Predicting the Popularity of Online News. Proceedings of the 17th EPIA 2015 - Portuguese Conference on Artificial Intelligence, September, Coimbra, Portugal.


Competition adapted from  "Data Science and Machine Learning 3: Tools" course, part of the [MSc in Business Analytics](https://economics.ceu.edu/program/master-science-business-analytics) program at CEU in the Winter semester of 2018/19 (https://www.kaggle.com/c/online-news-popularity/)