Machine Learning Competition

GMPH Machine Learning Specialisation

In this webpage you will be able to (i) submit your predictions for the test dataset available above, (ii) visualise your previous submissions, and (iii) visualise your ranking in the course leaderboard.

For each submission, please ensure that:

  • You upload a csv file made of a single column called 'illness'.
  • The 'illness' column only contains numbers between 0 and 1 or are empty.
  • The order of your predictions in the 'illness' column matches the order of the records in the test dataset above.

The metric used to calculate performances and establish the leaderboard is the logLoss:

$$\text{logLoss(}\textbf{y}\text{,}\widehat{\textbf{y}}\text{)} = - \frac{1}{n} \sum_{i=1}^n \left[ y_i \log(\hat{y}_i) + (1 - y_i) \log(1 - \hat{y}_i)\right] $$

When you are ready to make a submission, head to the 'Submit' tab on the right.

Good luck!

Download the training dataset and the test dataset .

Enter your Imperial email address (@ic.ac.uk or @imperial.ac.uk) to access the competition. We'll send you a verification link; follow it to confirm your identity. Returning students simply re-enter their email and re-verify.



© 2022, Imperial College London, All rights reserved.