Submissions will be scored by mean absolute error (MAE) across all values in the evaluation data.
Both the training and evaluation data sets have missing values, and our intention is to ignore these in calculating MAE. To do this, we have (in the solution file) transformed all NA's to "-1,000,000" and shown you where these occur by providing you with
 a sample submission that has these values in all of the correct places, and 0's everywhere else.