Women's Hack for Safety by Agence Française de Développement
Can you predict which women are at highest risk of being made a victim of a crime in South Africa?
Prize
$1,000 USD
Time
Ended over 1 year ago
Participants
130 active · 208 enrolled
Helping
Africa
Prediction
Safety
Description

Please note that this is a women’s-only hackathon, intended as a safe space for women to practice and learn from each other. Any men found on the leaderboard will be disqualified. We will check identity documents and conduct interviews with participants during and after the hackathon.

Welcome to the Zindi Women's Hack! This is a one-day virtual hackathon for the women data scientists of the Zindi community. Note that the dataset and leaderboard will be open for just one day on 10 April 2021. Review the Timeline section for the day's schedule. We encourage you to join us on the livestream on the day of the hackathon. See you then!

How to prepare for the hackathon

  1. Practice on a challenge and make your first Zindi submission. Watch this YouTube video.
  2. Make a team in preparation for UmojaHack. Watch this YouTube video.

South Africa has one of the highest crime rates in Africa, with approximately 2 million crimes reported every year. Women experience crime and are vulnerable to crime in different ways from men. Studies find that while men in South Africa are more likely to be a victim of any type of crime in general, women are more likely to be a victim of particular types of crime, including sexual assault and property damage, and on average feel more unsafe than their male counterparts.

We are calling on the women in data science to explore this issue with us. This challenge calls on you to build a machine learning model that predicts a woman’s level of risk of being victimized by a crime given basic information about her and her life.

About Agence Française de Développement (afd.fr/en)

The Agence Française de Développement (AFD) Group funds, supports and accelerates the transition to a fairer and more sustainable world. Focusing on climate, biodiversity, peace, education, urban development, health and governance, our teams carry out more than 4,000 projects in France’s overseas departments and territories and another 115 countries. In this way, we contribute to the commitment of France and French people to support the Sustainable Development Goals (SDGs).

About DataFirst (datafirst.uct.ac.za)

DataFirst is a research data service dedicated to giving open access to data from South Africa and other African countries. We promote high quality research by providing the essential Open Research Data infrastructure for discovering and accessing data and by developing skills among prospective users, particularly in South Africa. We undertake research on the quality and usability of national data and encourage data usage and data sharing.

About StatsSA (statssa.gov.za)

StatsSA’s vision is to improve lives through data ecosystems and to transform the production, coordination and use of statistics through optimization, partnerships and innovation.

Rules

Please note that this is a women’s-only hackathon, intended as a safe space for women to practice and learn from each other. Any men found on the leaderboard will be disqualified. We will check identity documents and conduct interviews with participants during and after the hackathon.

Teams and collaboration

You may participate in this competition as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the competition, minus the highest number of submissions among team members at team formation. Prizes are transferred only to the individual players or to the team leader.

Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be disqualified.

Code must not be shared privately outside of a team. Any code that is shared, must be made available to all competition participants through the platform. (i.e. on the discussion boards).

Datasets and packages

The solution must use publicly-available, open-source packages only.

You may use only the datasets provided for this competition. Automated machine learning tools such as automl are not permitted.

You may use pretrained models as long as they are openly available to everyone.

The data used in this competition is the sole property of Zindi and the competition host. You may not transmit, duplicate, publish, redistribute or otherwise provide or make available any competition data to any party not participating in the Competition (this includes uploading the data to any public site such as Kaggle or GitHub). You may upload, store and work with the data on any cloud platform such as Google Colab, AWS or similar, as long as 1) the data remains private and 2) doing so does not contravene Zindi’s rules of use.

You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the competition data, and work with Zindi to rectify any unauthorised transmission or access.

Your solution 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.

Submissions and winning

You may make a maximum of 100 submissions per day.

Before the end of the competition, you need to choose 2 submissions to be judged on for the private leaderboard. If you do not make a selection your 2 best public leaderboard submissions will be used to score on the private leaderboard.

Zindi maintains a public leaderboard and a private leaderboard for each competition. The Public Leaderboard includes approximately 50% of the test dataset. While the competition is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the competition, the Private Leaderboard, which covers the other 50% of the test dataset, will be made public and will constitute the final ranking for the competition.

If your solution places 1st, 2nd, or 3rd in the final ranking, you will be required to submit your winning solution code to us for verification and you thereby agree to share all worldwide rights of copyright in and to such winning solution to Zindi.

In the spirit of Zindi we hope that this can be a true womxn's hackathon where womxn can show their strength and encourage each other. Please do not share the secret code with men and please do not get help from outside your team.

The winners will be paid via bank transfer, PayPal, or other international money transfer platform. International transfer fees will be deducted from the total prize amount, unless the prize money is under $500, in which case the international transfer fees will be covered by Zindi. In all cases, the winners are responsible for any other fees applied by their own bank or other institution for receiving the prize money. All taxes imposed on prizes are the sole responsibility of the winners. The top 3 winners or team leaders will be required to present Zindi with proof of identification, proof of residence and a letter from your bank confirming your banking details.

You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this competition constitutes your acceptance of these official competition rules.

Teams may win in one challenge category, and are encouraged to enter only one

  • Participants may compete individually or in teams of up to four people.
  • The teams will be judged based on their ranking on the dedicated Zindi leaderboard at the time of competition close.
  • vAll participants in the hackathon must be womxn or identify as a womxn.
  • Teams cannot collaborate or share information with each other.
  • All solutions must use machine learning, but teams are permitted and encouraged to use exploratory data analysis in building their solutions.
  • All solutions must use publicly-available, open-source packages only.
  • Solutions must use only the allowed and available datasets.
  • Participants caught cheating or breaking any competition rules will be immediately disqualified from the competition.
  • The winning code must be submitted to Zindi for review and validation immediately at the close of the competition. In the interest of logistics, code review will take place only after the competition has closed and winners have been announced.

Please refer to the FAQs and Terms of Use for additional rules that may apply to this competition. We reserve the right to update these rules at any time.

Evaluation

The error metric for this competition is Area Under the Curve.

Your submission file should look like:

Where 1 indicates at least one incident of a crime and 0 indicates no crime.

ID        target
ID_91371   0.11
1D_10161   0.95
ID_124651  0.34
Prizes

To be eligible for a prize you need to be a female or identify as a female. We will require identification before payment of prizes.

1st Place: $500 USD

2nd Place: $300 USD

3rd Place: $200 USD

In the spirit of Zindi we hope that this can be a true womxn's hackathon where womxn can show their strength and encourage each other. Please do not share the secret code with men and please do not get help from outside your team.

Only one non-African can win one of the top three prizes.

Timeline

Sign-ups are open now, but the dataset and challenge will be open for only one day on 10 April 2021. The day's schedule is as follows:

All times are in GMT.

Follow us here on YouTube.

08:00 – 08:05 Welcome (live stream on YouTube link)

08:05 - 08:10 Peter Addo (AFD)

08:10 - 09:10 Panel moderated by Zindi CEO Celina Lee, with panelists including Zindi Ambassador from Sudan Reem Elmahdi, the head of the Makerere Artificial Intelligence and Data Science research Lab Dr. Joyce Nabende, & software engineer and data scientist Rose Wambui.

09:10 - 09:20 Rules and intro to challenge

09:20-09:30 Technical intro with Rose Wambui

09:30 Competition opens (note that users can sign up for a competition and join teams before the time)

09:30 – 18:00 Students form teams and work on the challenge, questions and issues during this time can be addressed by local Zindi reps or via WhatsApp group

18:00 Submissions close

18:15-18:30 Announcement of winners and prizes (live video conference on YouTube)

Mentorship

In partnership with AFD, Zindi is launching a Women's Mentorship Programme where promising young female data scientists have the opportunity to be mentored by the best women data scientists on Zindi's platform. This is open to any level from beginner to intermediate.

If you think you can be a rising star in the African data science scene and you could benefit from a mentor, fill out this application form for a chance to be selected for this exciting new programme. Please note that places are limited, so make sure you fill this application out to the best of your ability. The deadline to complete the form is Tuesday 20 April 2020 12:00 GMT.

We aim to start the program in May 2021. The program will run for appoximately 8 weeks and will require a minimum of 2 hours per week.

If you do not hear from us by 31 April 2021, it means that you were not selected for this cohort, but we will keep your application on file for future opportunities. Thank you for your application!

This application is open only to women.

(If you are an experienced data scientist and are interested in the opportunity to help develop and guide the next generation of female African data scientists, please complete this application form to act as a mentor.)