The evaluation metric for this competition is accuracy (% correct). The data has been split 70/30 into a labeled training set and an unlabeled testing set. You will be submitting your predictions on the testing set. When you submit a set of predictions, you will receive an accuracy score based on a randomly-sampled 50% of the test set (the random sample will be constant across submissions). This score will show up on the competition's leaderboard. Your final score will be based on your accuracy on the whole test set, and will be released once the competition has closed.
Rewards
Top 5 groups counting only their best submission on the private leaderboard get the following rewards:
1st - 3pts
2nd - 2pts
3rd - 2pts
4th - 1pt
5th - 1pt
Each group is limited to 2 submissions per day.
Submission Format
A sample submission csv file has been provided. Your submission should have headers (PassengerID,Survived) with two columns of output- the passenger id and the prediction for survival (1 for survived, 0 for did not survive). Kaggle will interpret each class prediction as a string ('1' vs '0'), so make sure your survived column does not include decimal places.