Goal
It is your job to predict how many times an article will be shared online (target variable name: "shares"), given the ~60 columns containing a summary about the content of the article, temporal features, features associated with metadata of the article, and features pulled from other NLP models run on the data.

Metric
Submissions are evaluated on Root-Mean-Squared-Error (RMSE) between the value of the predicted value and the actual value of # of shares for each article.

RMSE formula

The public leaderboard is going to rank your submission against other users while the competition is active, however, once the competition is ended, the final ranks will be calculated on the private leaderboard.

Submission file format
The file should contain a header and have the following format (CSV):

id,shares
29733,3262.0
29734,802.0
29735,953.0
etc.
A sample file can be found attached in the Data section of this competition.