The prediction of your classifier will be evaluated by using *accuracy*:
\[
Acc = \frac{1}{n}\sum_{i=1}^{n}(y_i==\hat{y}_i)
\]
where n is the number of instances.
Submission Format
The submission file should be in text format (.csv). The submission file must have the following format:
\[
\begin{array}{cc}
Id & Category\\
0 & 1\\
1 & 0\\
2 & 1\\
3 & 1\\
4 & 0\\
... & ...\\
\end{array}
\]
where *Id* is the Id of the person (the first column of the dataset) and Category is your prediction for that person (1: approved, 0:denied).  Be sure that  the values in the Id and Category column are integers (not float).