Standard Bank Tech Impact Challenge: Animal classification
Create a binary classification algorithm to distinguish zebras from elephants
309 data scientists enrolled, 63 on the leaderboard
ConservationComputer VisionGood for BeginnersUnstructuredImageSDG15
30 August 2019

This challenge is an invitational challenge designed in association with Standard Bank, specifically for the Standard Bank Tech Impact Challenge (SBTIC) Finals. Welcome to the SBTIC participants!

If you are at the SBTIC Finals taking place from 30 August to 3 September 2019 in Johannesburg, South Africa, you may enter this challenge by giving your email address to the Zindi representative.

After the SBTIC, this competition will be re-opened as a Knowledge Challenge to allow others in the Zindi community to learn and test their skills.

The objective of this challenge is to create a machine learning model to accurately predict the likelihood that an image contains a zebra, as opposed to an elephant. While this may be an easy task for humans, elephants, and zebras, your computer will find it a bit more difficult.

The total dataset contains 18,000+ images of zebras and elephants, sampled from the Snapshot Serengeti collection of more than 6 million animals. The data was retrieved from the Data Repository for the University of Minnesota,, under a creative commons license, from a study titled: Camera Trap Images used in "Identifying Animal Species in Camera Trap Images using Deep Learning and Citizen Science".*

“Hundreds of camera traps in Serengeti National Park, Tanzania, are providing a powerful new window into the dynamics of Africa’s most elusive wildlife species. We need your help to classify all the different animals caught in millions of camera trap images. This grid of camera traps has been operating continuously since 2010 and has produced millions of images, which our amazing volunteers classified!” For more info on the Snapshot Serengeti, please visit:

This challenge is being hosted in association with Standard Bank.

About the Standard Bank Tech Impact Challenge

The Standard Bank Tech Impact Challenge (SBTIC) is a competition for teams of students in South African tertiary institutions, at undergraduate and honours level, to demonstrate their programming ability and teamwork capabilities with limited resources.

Each of the participating tertiary institutions enters a number of teams. The teams attempt to solve as many problems as possible during the Heats, which take place at the tertiary institutions during the first half of the year. The top teams from the the top 15 institutions are then invited to the Finals in Johannesburg. The winning student teams and tertiary institutions receive prizes as outlined in the SBTIC rules and terms and conditions.

In 2019, the theme of the SBTIC is Machine Learning and Artificial Intelligence and the winners will be awarded and recognised for show-casing their engineering excellence, creativity and innovation.

For more information, please visit the Standard Bank Tech Impact Challenge Website.

* Full citation: Willi, Marco; Pitman, Ross T; Cardoso, Anabelle W; Locke, Christina; Swanson, Alexandra; Boyer, Amy; Veldthuis, Marten; Fortson, Lucy. (2018). Camera Trap Images used in "Identifying Animal Species in Camera Trap Images using Deep Learning and Citizen Science". Retrieved from the Data Repository for the University of Minnesota,