The evaluation metric for this competition is the
[ROC-AUC Score/Metric](https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve)
. This means you can submit probabilities instead of 1's and 0's. More specifically, predict the probability of a "1" (mid price strictly increases) occurring.

### The AUC metric

Due to AUC's computation method (vary a decision threshold and calculate an integral), the exact class probability is not important for prediction, only the relative probabilities between the predictions. Unless you are trying to aggregate multiple different model classes, you do not need to worry much about calibrating the exact probability.
Submission Format
For every timestep (id) in the test.csv dataset
, submission files should contain an associated probability of the mid price strictly increasing in the next 2 timesteps. See the sample submission for an example.