How to Prepare for UmojaHack Africa 2021

So your university has signed up for UmojaHack Africa 2021. Congratulations! You’re now a part of Africa’s biggest machine learning hackathon! But what now? Here are the steps you can take (as a university or as an individual) to prepare for the weekend.

For universities

  1. Share the event: With just a few weeks to go, now is the time to recruit as many students as possible! Please share the flyer below with as many interested students and student groups as possible and try to drum up excitement.
  2. Send out a registration form: Zindi does not track individuals registrations for UmojaHack Africa 2021, rather relying on university organisers to keep track of participants at their university. Please use Google Forms, a spreadsheet, or email list to keep track of individuals interested in the event. This will help us in sharing access codes for the competition at the start of the event, as well as sharing details of the livestream.
  3. Encourage participants to sign up on Zindi and practice: Students will need to be signed up to Zindi in order to participate, so please make sure everyone at your university is signed up. They should also be sure to add their university to their profiles – you can find out how to do this using this article. Students can also take the next few weeks to practice their ML skills using other competitions on Zindi – our Knowledge competitions are a good place to start for those not familiar with data science competitions or the Zindi platform.
  4. Prepare for a physical or virtual hackathon event on 27-28 March: It is up to each university whether they want to host a virtual or physical events. Physical hackathon events are always exciting and full of energy, but require more organisation and may not be feasible during COVID-19 lockdown conditions. If you are hosting a physical event, we recommend setting up a screen or projector for the ongoing livestream, securing food or drinks for competitors, and making sure you have a good internet conenection and sufficient computing power for the event – ML competitions are resource-intensive! We will also be connecting with physical events around Africa, so if you want to be a part of the stream you can set up a camera to stream from your location.

For data scientists and students

  1. Sign up on Zindi: To participate in UmojaHack Africa 2021, you need to have a Zindi account and it would help to familiarise yourself with the platform. Sign up here and follow these instructions to add your university to your profile.
  2. Take a look at the challenges: There will be three different machine learning challenges to choose from on the weekend of the event. These challenges are designed to present a challenge to beginner (<1 year data sceince experience), intermediate (1-2 years’ data science experience), or advanced (2+ years’ data science experience) users. So don’t worry, there is a challenge for everyone!
  3. Practice on similar challenges: With a few weeks to go, the best way you can prepare right now is to practice your m,achine learning skills on Zindi. This will help you get familiar with the patform and also build some skills in the type of competition you might be facing during UmojaHack Africa 2021. You can read more about the challenges and see similar challenges below, or just pick from Zindi’s many Knowledge competitions that include starter notebooks and tutorials.
  4. Tell your friends and fellow students: Data science is a team sport! Make sure to bring your friends and fellow students to the event – you will have more fun and learn more together.

More about the challenges

The Beginner Challenge: Predicting Financial Resilience

UmojaHack Africa: Financial Resilience Challenge

Can you predict if an individual will be able to make a payment in an emergency situation?

Financial resilience is the ability to withstand and recover from temporary, unexpected life events that can cause financial hardship. These events can include unemployment, divorce, disability, and health problems. As we move into the second year of the global pandemic, resilience matters now more than ever.

This challenge asks you to build a machine learning model to predict which individuals across Africa and around the world are most likely to be financially resilient or not.

Similar challenge for practice: Financial Inclusion in Africa | Tutorial for this challenge

The Intermediate Challenge: Sendy Logistics

UmojaHack Africa: SENDY Delivery Rider Response Challenge

Can you predict who is the best delivery rider for an order placed via logistics company Sendy?

Sendy links customers who have delivery needs with vetted transporters (from bikes to trucks), using a web and mobile application platform as well as an API. The system optimises the route and dispatches the order to the closest available drivers and riders.

The objective of this challenge is to create a machine learning model that will predict whether a rider will accept, decline or ignore an order sent to them.

Similar challenge for practice: Fraud Detection in Electricity and Gas Consumption Challenge

The Advanced Challenge: Designing Antibodies for Influenza

UmojaHack Africa: DEEPCHAIN ANTIBODY CHALLENGE

Evaluating neutralising antibodies for the next influenza pandemic using the DeepChain.bio platform

There is a need to develop neutralising antibodies that can target any new flu variants that might escape current vaccines’ protection. One dangerous strain of the virus that may cause a pandemic in the future is the highly pathogenic H5N1 variant of influenza A virus. Thus, the design of a neutralising antibody targeting this influenza virus could offer enormous therapeutic potential. 

Your challenge is to use InstaDeep’s DeepChain.bio platform to evaluate the strength of a neutralising antibody against the extremely virulent H5N1 influenza variant.

Similar Challenge for practice: InstaDeep Enzyme Classification Challenge

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s