Each participating team can have at most one submission per day in the public leaderboard phase and only ONE submission in the final phase. The performance in the public leaderboard phase is expected to help participants improve their model. The ranking of the participating teams is decided using a final validation set independent of the test data used in the public and private leaderboard estimation.

The primary metric for this competition is [Quadratic Kappa Metric](https://www.kaggle.com/code/aroraaman/quadratic-kappa-metric-explained-in-5-simple-steps/notebook). 

For the final evaluation, in addition to the point estimates calculated on the final validation set (scores calculated by Kaggle), we will also apply a bootstrapping resampling to identify statistically tied top-performing teams. To this end, we will draw 1000 bootstrapped samples (with replacement) from the final validation set to generate the distribution of each model'  Kappa score. A Bayer factor, Km will be calculated for each team's final model, with the model showing the highest point estimation as the reference. 

As a consequence, participants that want to officially win the competition and the prize need to share their algorithms. However, sharing algorithms is not required to test your skills and take part in the competition. 



## Submission Format

**For every compound in the test dataset**, submission files should contain two columns: `Id` and `Pred`. 


The file should contain a header and have the following format:
```
Id,Pred
1,1
```