We have published the source code of early baseline to inspire you and show an example of preprocessing on the competition data. You can find it in data files section or download it directly using the link https://knowledgepit.ml/competition_file_download/87/ .
The code is written as R notebook, but you should be able to understand the main ideas even if you are not so familiar with this language.
We have also decided that probably we won't be publishing any new baseline, so you have to beat the early baseline by 10% to be eligible for the prices.
Let me know if you have any questions. Good luck!
on behalf of the Organizing Committee
Update: I have also uploaded the html showing output of every code cell, I hope you it will help you better understand the code.