Submissions are evaluated on the Mean Absolute Error (MAE) between the predicted horse speed and the actual horse speed. MAE measures the average magnitude of errors between predicted and actual horse speeds. It's calculated as:

MAE = (1/n) * SUM(absolute(y_i - yhat_i))

Where:
- n is the number of observations.
- y_i is the actual horse speed for the ith race.
- yhat_i is the predicted horse speed for the ith race.

Participants should aim to minimize the MAE for a higher leaderboard position. The closer the MAE is to zero, the better the predictions.

## Submission File
For each ID in the test set, participants must predict the horse speed. The file should contain a header and have the following format:

    ID,Horse_Speed
    2023-01-01_13:00:00,15.5
    2023-01-01_13:01:00,16.2
    2023-01-01_13:02:00,15.8
    etc.

Use the provided sample submission file as a reference for the expected format.