### Use only the given data files

Since data is subsampled from an original competition you should train only on the given subset of data. You can use weakly supervised techniques however, using unspecified training data from original competition (train or test) is not allowed.

### One account per participant

You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.

### No private sharing outside teams

Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.

### Team Mergers

Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.

### Team Limits

There is no maximum team size.

### Submission Limits

You may submit a maximum of 2 entries per day.

You may select up to 2 final submissions for judging.

Competition Timeline

Start Date: 11/10/2017 12:00 AM UTC

Merger Deadline: None

Entry Deadline: None

End Date: 7/11/2017 11:59 PM UTC

Grading criteria is common to both assignments. We replicate it here for your convenience (For any potential conflicts with the announcement on IVLE, please base the version on IVLE) :

40% on Documentation, which consists of:
20% on the documentation itself: formatting, clearness, comprehensiveness of your README, as well as how well your team complies with the competition rules. 
20% on the creativity, insight or depth of your solution. 
60% on Relative Performance:
10% on Training data performance (as reported by you)
25% on Given testing performance (as reported by Kaggle)
25% on Held-out testing performance (not available for testing against in Kaggle, will be compiled by our TA group.
Two important details about the deliverables:

1) README.pdf. Your README (in .pdf) needs to contain a short 1-3 page report detailing how your team tackled the task, inclusive of documenting any data analysis you performed on the data, normalization, models tried, and any post analysis that you did. In addition to the report, you need to also describe the files that are submitted, include your statement of independent work (or suggest alternative evaluation criteria), and a section of the references you used in your project.

2) Held out testing set. Kaggle makes both the training and testing data available for you to download. Since both problems' full datasets are publicly available, you could recover the labels for the test sets that we provide you, but this regards as cheating. Therefore it is not allowed and all teams should not attempt to use the original public datasets to reconstruct the testing data that is hosted on Kaggle. Such cheating defeats the purpose for the assignment, and your team would be better off investing effort in learning how to apply ML appropriately instead of wasting time to circumvent our efforts to give you a genuine learning problem. Offending teams will be severely prosecuted.


We will also construct new data on our own which we do not provision to Kaggle (held-out testing data), which is given an equal weight in the grading.

We will be asking you to demonstrate your team's learner on new instances within X days after Homework #3's submission deadline, to establish held-out testing performance. These dates and the workflow process details will be announced later.