14 April 2020

Women in Big Data SA partnered with Zindi Africa to run a Womxn in Big Data South Africa: Female-Headed Households in South Africa Challenge.

Female household headship has been on the rise in South Africa in recent years. Compared to male-headed households, female-headed households tend to face greater social and economic challenges. Female-headed households, in general, are more vulnerable to lower household incomes and higher rates of poverty.

The South African census collects data on female headship and income levels of every household across the country every ten years. However, it is important for policymakers and other actors to have accurate estimates of these statistics even in-between census years. This challenge explores how machine learning can help improve monitoring key indicators at a ward level in-between census years.

The objective of this challenge is to build a predictive model that accurately estimates the percent of households per ward that are female-headed and living below a particular income threshold by using data points that can be collected through other means without an intensive household survey like the census.

This solution can potentially reduce the cost and improve the accuracy of monitoring key population indicators such as female household headship and income level in between census years. The winning solutions will be made publicly available at the end of the competition.

This competition is sponsored by Women in Big Data South Africa and Microsoft, in collaboration with HERE Technologies.

The challenge ran from 25 November 2019 – 24 February 2020, and we are so excited to finally celebrate the winners with our community.

A big thank you to everyone who participated: 452 data scientists from 41 different countries enrolled in the challenge. Sadly we had to pick only three winners. All submitted projects were wonderful, and we are grateful to be walking with such wonderful talent in this journey.

Meet The Winners

Congratulations to these amazing ladies for making it to the top three: Ansem Chaieb (first prize), Lucille Kaleha (second prize), and Sirine Bouslama. We are happy and excited to know you and introduce you to the team.

Q&A: with Ansem Chaieb

How did you get to choose a career in Tech?

Due to my love for mathematics, programming and analyzing data I choose such field since I think data science cuts across pretty much every field science, engineering, health care, energy sector, technology, etc.

What are the challenges you faced as a beginner, and are you are still facing them now?

The biggest challenge I’ve had as a beginner is explaining technical concepts to non-technical audiences. But I’ve tackled this problem by participating in presentation competitions where you have to explain your work to business people who may not understand the complexity of your work if you can’t explain what your model does, and through this participation I’m learning new skills every time.

What still inspires you to continue and get better in your career?

Data science is a good fit for what I’ve been doing and enjoying since it’s a real challenging domain that helps me to make an impact, and one of the most inspiring domains is Reinforcement Learning in Games and how RL agents beat real world champions.

Advice you would give to girls that are aspiring in getting into Tech but are scared they won’t succeed?

The best way to learn in the tech field is to jump in and build things, so you should go ahead and do that as much as possible. Don’t be intimidated by those who seem to know more than you. Never be afraid to ask questions if you don’t understand something. It’s a great way to learn. So believe in yourselves. Go out, build stuff, break stuff and state your ideas and opinions with confidence. And remember – those doubts and fears, they’re just in your head.

What has been the highlight of your journey?

I consider that winning the “Women in Big Data” competition on the Zindi platform is one of my greatest achievements that motivates me and enhances my career.

Any woman in the field who inspires you?

I really appreciate the work of Emily Glassberg Sands (the head of Data Science at Coursera) and how she cares deeply about the mission of providing life-transforming learning and credentials at scale.