**Evaluation**:

The evaluation criteria for the **Global Dengue Outbreak Prediction Challenge** are designed to measure how well the participants' models predict the number of dengue cases. The goal is to minimize the error between the predicted values and the actual number of cases.

Submissions will be evaluated using the **Mean Absolute Error (MAE)**. MAE is a risk metric corresponding to the expected value of the absolute error loss or \( l1 \)-norm loss.

$$ \text{MAE} = \frac{\sum_{i=1}^{n} |y_i - \hat{y}_i|}{n} $$

******Where******:
- \( y_i \) is the actual number of dengue cases,
- \( \hat{y}_i \) is the predicted number of cases,
- \( n \) is the number of observations in the test set.

The MAE reflects the average magnitude of the errors in a set of predictions, without considering their direction. It’s particularly useful in this competition because it quantifies the accuracy of predictions regardless of whether the predicted values are over or under-estimates.

---

## Submission File

Participants must submit their predictions in a `submission.csv` CSV file with a header. For each observation in the test set, participants will provide an ID and their predicted count of dengue cases. The file should have the following format:

```
ID,PredictedCases
1,12
2,5
3,8
etc.
```

All submissions should be evaluated by the competition’s automated system, and results will be reflected on the leaderboard. Ensure that the submissions are in the correct format to avoid any disqualification or incorrect scoring.