The evaluation of the challenge will consist of 2 parts:

### 1. Detection Score
We use the F-beta-score with a beta value set to 1.75 as the error metric. You can find more information about the F-beta-score [here](https://medium.com/@douglaspsteen/beyond-the-f-1-score-a-look-at-the-f-beta-score-3743ac2ef6e3). You can view the score of your submission based on the error metric on the leaderboard at any time. Here you can also see how well your algorithm performs compared to other teams. It is important to note that the leaderboard does not show the final score as it is only determined based on around 37% of the test data. We will use the other 63% of the test data only at the end of the challenge for a final evaluation.

### 2. Best Complete Package
We are not only interested in the pure error score but also in your ideas. Participants are invited to present their solutions at the final event. There we will crown the winner for the best overall solution approach. The price for this category will be awarded by the participants themselves as a community decision.