Submissions are scored on the log loss:
$$
\textrm{LogLoss} = - \frac{1}{n} \sum_{i=1}^n \left[ y_i \log(\hat{y}_i) + (1 - y_i) \log(1 - \hat{y}_i)\right],
$$
where
n is the number of patients in the test set
\\( \hat{y}_i \\) is the predicted probability of the image belonging to a patient with cancer
\\( y_i \\) is 1 if the diagnosis is cancer, 0 otherwise
\\( log() \\) is the natural (base e) logarithm
Note: the actual submitted predicted probabilities are replaced with \\(max(min(p,1-10^{-15}),10^{-15})\\). A smaller log loss is better.
Submission File
For each patient id in the test set, you must submit a probability. The file should have a header and be in the following format:
id,cancer
01e349d34c02410e1da273add27be25c,0.5
05a20caf6ab6df4643644c923f06a5eb,0.5
0d12f1c627df49eb223771c28548350e,0.5
...