This is a **Binary Classification Task**. The evaluation metric for the Leaderboard on this challenge is the **Micro F1-Score**. This would allow us to evaluate your model in terms of its specificity and sensitivity. 
In addition to it, **all the teams would be required to submit a 1-2 page report and codes** explaining their approach for our judges to decide on the winning teams. Although a higher position on the Leaderboard is a plus, **Novelty and Performance** will be the deciding factor for the winners.
Notifications through the mail will be sent to the registered participants about the report format and submission procedure.

---

The Leaderboard's Micro F1 score measures accuracy using the statistics of precision and recall. It is given by:

$$\text{F1} = \frac{tp}{tp + \frac{1}{2}\cdot (fp + fn)}$$

where tp is the true positive, fp is the false positive and fn is the false negative.

## 📋 Submission Format

**For every participant**, the `.csv` submission file should contain two columns: `id` and `label`. 

- `id` is the id of the audio file 
- `label` is the predicted label for that audio file.

The `.csv` file should contain a header and have the following format:
```
id,label
1,1
```
Check out `sample_submission.csv` in the [Data section](https://www.kaggle.com/competitions/datafestintegration2023/data) for more info.

---

## 💯 Scoring
The following describes how the final scores would be obtained for each team,
- A weighted average of scores given by the cohort of professors and industry experts on both submissions, i.e. the Whale Sound Classification Challenge and the Bonus Problem, independently will be used to arrive at the final score given to the teams.
- The Bonus Problem is more challenging compared to the [Whale Sound Classification](https://www.kaggle.com/competitions/datafestintegration2023) and hence the weightage for the Bonus Problem's score is strictly greater than that of the whale challenge.
- In case no submission is made to the bonus problem, the score for the bonus problem will be considered to be 0.
- In case no submission is made to the Whale Sound Classification problem, the score for that will be considered to be 0.