Submissions are evaluated using the Macro-Averaged F1 Score, which is the mean of the F1 scores calculated for each class. The F1 score, a measure of a test's accuracy, is calculated using the formula:



$$ F_1 = 2 \times \frac{\text{Precision} \times \text{Recall}}{\text{Precision} + \text{Recall}} $$



Where:

Precision is the ratio of correctly predicted positive observations to the total predicted positives.
Recall is the ratio of correctly predicted positive observations to all observations in the actual class.
The Macro-Averaged F1 Score is then computed as:

​
$$ F_{1\text{macro}} = \frac{1}{C} \sum_{c=1}^{C} F_{1c} $$



Where:

C is the total number of classes (in this case, 2: up or not up).
F1_c is the F1 score for class c.
This evaluation metric ensures that the model performs well across both classes, balancing the precision and recall to provide a comprehensive assessment of its accuracy.