As Zindi grows into a global data science competition platform, it’s important that we regularly revisit the systems and rules we have in place, to make sure Zindi remains your favourite place to solve machine learning challenges.
Based on recent feedback and activity on the platform, we are updating our submissions policy and competition rules. You can read our new rules and competition guidelines at the end of this post.
We are also making longer-term changes to the platform to limit the incidence of cheating and improve the experience the vast majority of you have on the platform. These changes will serve to streamline and professionalise our code review process, eliminate data leaks, and reduce the frequency and impact of cheating on the platform.
Effective immediately, we will be implementing new stricter rules for code submissions. In addition to systematically requesting code from the top 3 submissions, we will now reserve the right to request code from the top 20 users/teams on each leaderboard at the close of each competition. Your code submission must follow the guidelines below:
If submission code does not reproduce your score on the leaderboard, we will drop your rank to your closest submission to the solution actually generated by your code.
If your code does not run you will be removed from the leaderboard. Please make sure your code runs before submitting your solution.
Please take a moment to review the full submission guidelines below.
If an individual or a team is caught cheating, all team members:
Anyone caught cheating a second time will:
We have taken steps to put a more rigorous review process in place for all competitions, but we acknowledge that it is not always feasible or possible for us to determine potential data leaks before the start of a competition.
If a leak is found, the leak will be made public. You can see how to report a leak below. In order to preserve the value of the competition and ensure the final solutions are both valid and useful, Zindi reserves the right to update the train and test set, close or relaunch a challenge in response to a data leak.
If you notice suspicious activity, or find a potential data leak, we urge you to report it immediately. You can report suspected cheating or a data leak by sending an email to firstname.lastname@example.org.
If you suspect another user or a team of cheating or otherwise abusing the platform, kindly provide any supporting evidence you can. Our team will then review this and take the necessary steps to validate and act on the claims made.
We will be reviewing suspicious behaviour during the course of our competitions and may request to see code at any time during a competition. Should we request your code during a competition, you will have 24 hours to submit your code for review, or face disqualification.
Finally, in order to aid transparency, we will be adding the number of submissions for each user/team to the competition leaderboards.
The integrity of the Zindi platform is of utmost importance to us, as it is to you. We are committed to doing everything we can to make sure that legitimate efforts on Zindi are recognised and rewarded fairly while unethical behaviour is sanctioned and strongly discouraged. We’d like to thank everyone on the platform for complying with these rules and making Zindi a safe and welcoming competitive space for data science.
This is a good move.Quick question, Are you going to extend the award to top 20.Currently it's only top 10 who receive awards(cash prize /Zindi points)
Thank you Zindi for listening to the users' feedback, and for updating the rules in a way that will make it harder for users to abuse old rules for personal benefit. This will not only make your usual competitors complain less ( yes i complain a lot ), but will make you retain newcomers when they see action is being taken by YOU to give all of us a better competing experience.
Also does the code reviewing apply to Zindi Points challenges or only money prizes ones?
Suggestion 1 :
It would be more discouraging for users to privately share if the logged behavior of a competitor is reviewed against other users' behaviors either by a handpicked number of users to ensure no one has been submitting similar scores with other users on the same time, or by an employee of yours. First option is better, you can , after each competition, let users sign up to receive a csv file containing all information about submissions by all users in a competition. If something is caught, it can be reviewed by this group and voted on.
Since many competitions require someone to be African or a woman, I think it should be encouraged by Zindi for everyone to identify themselves by country and gender from the start to avoid falsification and to better track a person's origin.
Submissions by former teammates around the same time and around the same score are highly suspicious. Please make it clear that sometimes, if you are considering making a team and you haven't decided it, do not privately share ( i speak from personal experience ). This type of behavior is suspicious, and it would be reasonable to take actions against it in other platforms.
Great annoucement ! We are getting close to the fun of competition. I even thought that ML competitions were just for cheating. But with this annoucement you are winning some competitors back.. :)
Your submission must use the most up-to-date packages : I think this rule is useless, we can juste send notebook with package.__version__ . with a new version of some packages with some packages there are bugs, so ...