3 Mar 2020, 12:58

ANNOUNCEMENT: Important updates to Zindi’s rules and submission guidelines

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.

New submission guidelines

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:

  • Your submission must run on the original datasets provided on the competition page
  • Your submission must use the most up-to-date packages and you may not use custom packages
  • Your code must be submitted within competition deadlines (usually 48 hours after close of challenge)
  • Your code must stick to good coding practice and you must provide full documentation

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.

Consequences for cheating

If an individual or a team is caught cheating, all team members:

  • will receive a formal warning
  • will be disqualified from the challenge(s) they are currently involved in
  • will be disqualified from winning points or prizes for six months

Anyone caught cheating a second time will:

  • have their account disabled and be permanently banned from the platform
  • be banned from creating a new Zindi account

Steps to limit data leaks

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.

How to report suspected cheating or 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 zindi@zindi.africa.

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.

Other platform changes

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.

Zindi Policy on Code Review and Cheating

If you are in the top 20 at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 48 hours to respond and submit your code following the submission guidelines detailed below.

Reproducibility

  • If your submitted code does not reproduce your score on the leaderboard, we reserve the right to adjust your rank to the score generated by the code you submitted.
  • If your code does not run you will be dropped from the top 10. Please make sure your code runs before submitting your solution.
  • Always set the seed. Rerunning your model should always place you at the same position on the leaderboard. When running your solution, if randomness shifts you down the leaderboard we reserve the right to adjust your rank to the closest score that your submission reproduces.
  • We expect full documentation. This includes:

- All data used

- Output data and where they are stored

- Explanation of features used

- Your solution must include the original data provided by Zindi and validated external data (no processed data)

- All editing of data must be done in a notebook (i.e. not manually in Excel)

Data standards:

  • Your submitted code must run on the original train, test, and other datasets provided.
  • If external data is allowed it must not exceed 1 GB. External data must be freely and publicly available, including pre-trained models with standard libraries. If external data is allowed, any data used should be shared on the discussion forum.
  • Packages:

- You must use the most recent versions of packages. Custom packages in your submission notebook will not be accepted.

- You may only use tools available to everyone i.e. no paid services or free trials that require a credit card.

Consequences of breaking any rules of the competition or submission guidelines:

  • First offence: No prizes or points for 6 months. If you are caught cheating all individuals involved in cheating will be disqualified from the challenge(s) you were caught in and you will be disqualified from winning any competitions or Zindi points for the next six months.
  • Second offence: Banned from the platform. If you are caught for a second time your Zindi account will be disabled and you will be disqualified from winning any competitions or Zindi points using any other account.

Monitoring of submissions

  • We will review the top 20 solutions of every competition when the competition ends.
  • We reserve the right to request code from any user at any time during a challenge. You will have 24 hours to submit your code following the rules for code review (see above).
  • If you do not submit your code within 24 hours you will be disqualified from winning any competitions or Zindi points for the next six months. If you fall under suspicion again and your code is requested and you fail to submit your code within 24 hours, your Zindi account will be disabled and you will be disqualified from winning any competitions or Zindi points.

Further updates and rulings of note:

  • Multiple accounts per user, collaboration or membership across multiple teams are not allowed.
  • Code may not be shared privately. Any code that is shared, must be made available to all competition participants through the platform.
  • Solutions must use publicly-available, open-source packages only, and all packages must be the most updated versions.
  • Solutions must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.
  • You will be disqualified if you do not respond within the timeframe given in the request for code.

We reserve the right to update these rules at any time.