Introduction to the challenges: UmojaHack Africa 2021

UmojaHack Africa is less than two weeks away, and now is the time to start preparing! Below you can read more about the challenges you can choose from on the weekend of 27-28 March 2021. We’ve also included some suggestions for similar challenges for you to practice on, so gather you team and start preparing!

Remember that in order to join a challenge, your university must be registered for the event (you can check on this list), and you will need an access code from your universitiy representative which they will share with you by 22 March.

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 classification 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

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

Updated university list: 126 universities from 21 countries enrolled

Check the list below to make sure your university is enrolled for this exciting event, and to find out who your university representative is!

LAST UPDATED: 26 MARCH

Abubakar Tafawa Balewa UniversityNigeriaGideon George
Academic City University CollegeGhanaDeborah Kanubala
Adama Science and Technology UniversityEthiopiaGenet Shanko Dekebo
Adventist University of Central AfricaRwandaJean Salvi Dukuzwenimana
Africa UniversityZimbabweYollanda Washaya
African Institute for Mathematical Sciences (AIMS Cameroon)CameroonTchangmena A Nken Allassan
African Institute for Mathematical Sciences (AIMS Ghana)GhanaBernard Oduoku Bainson
African Institute for Mathematical Sciences (AIMS Senegal)SenegalFranck Kalala Mutombo
African Leadership UniversityRwandaPerez Ogayo
Ahmadu Bello UniversityNigeriaMustapha Abdullahi Jimoh
Al Neelain UniversitySudanMansour Hassan Osman
Alioune Diop University of Bambey (UADB)SenegalFodé Camara
Alriyadah College For Business Managment & TechnologySudanMohammed Nour
Bayero University KanoNigeriaMustapha Muhmad Ibrahim
Bells University of TechnologyNigeriaNwoke Tochukwu
Bindura University of Science EducationZimbabweCharnelle Chikomo
Cairo UniversityEgyptDoaa Saleh
Carnegie Mellon University Africa (CMU Africa)RwandaInes Manzi
Central UniversityGhanaJoel Kwesi Appiah
Chinhoyi University of TechnologyZimbabweLeo Dzingirai
Chuka UniversityKenyaJoshua Abok Nyajuaya
CK Tedam University of Technology and Applied SciencesGhanaEdward Y. Baagyere
Dakar Institute of TechnologySenegalNicolas Poussielgue
Daystar UniversityKenyaErickson Odiaga
Dedan Kimathi University of TechnologyKenyaCiira Maina
Ecole Marocaine des Sciences de l’Ingénieur (EMSI)MoroccoEl Mehdi El Ouakifi
Ecole Nationale d’Electronique et des Télécommunications de Sfax (ENET’COM)TunisiaAchraf Mtibaa
Ecole Nationale des Sciences de l’informatique (ENSI)TunisiaMaher Abbes
Ecole Nationale PolytechniqueAlgeriaSouames Mohamed Annis
École Nationale Supérieure d’InformatiqueAlgeriaKhaled Afif Boudaoud
Ecole Nationale Supérieure d’Informatique Sidi Bel-AbbesAlgeriaAhmed Mounsf Rafik Bendada
Ecole Nationale Supérieure Polytechnque de YaoundéCameroonBatchakui Bernabé
Ecole Polytechnique de TunisieTunisiaMelik Sahraoui
Ecole Supérieure Africaine des Technologies de l’Information et le Communication (ESATIC)Côte d’IvoireKissi Amien Emmanuel
EIGSI (Ecole d’Ingénieurs Généralistes en Systèmes Industriels) CasablancaMoroccoInès Benhassen
Ekiti State UniversityNigeriaAdesina Abdulrahman
ESPRITTunisiaTunisia
Faculté de Sciences Tunis ManarTunisiaEmma Saadi
Federal University of Agriculture AbeokutaNigeriaSteven Kolawole
Federal University of Petroleum ResourcesNigeriaChiman Wakis
Federal University of Technology AkureNigeriaLawrence Okegbemi
Federal University of Technology MinnaNigeriaEmmanuel Atom
Federal University of Technology OwerriNigeriaChuka Ezeoguine
Great Zimbabwe UniversityZimbabweGrace N Majeke
Higher Institute of Applied Sciences and Technology of SousseTunisiaTaha Rehah
Higher School of Communication of Tunis (SUP’COM)TunisiaAyoub Chammam
Higher Technological InstituteEgyptMohamed Alaa Mohamed (Mido)
Information and Communications UniversityZambiaMoses Mupeta
Institut National Félix Houphouet BoignyCôte d’IvoireSuy Bi Trah Marcel William
Institut Superieur d’InformatiqueTunisiaWassim Henia
Institut supérieur des Technologies de l’information et de la communication (ISTIC)TunisiaHosni Boughanmi
International Data Science InstituteCôte d’IvoireAurel Céphas Ogoudjobi Attere
ISBAT UniversityUgandaMaki Dhedda Salomon
IT Business SchoolTunisiaAhmed Ben Taleb
Jomo Kenyatta University of Agriculture and Technology (JKUAT)KenyaPhilip Apodo Oyier
Kabarak UniversityKenyaBilly Gareth Otieno
Karatina UniversityKenyaSolomon Kimunyu Ndegwa
Kwame Nkrumah University of Science and TechnologyGhanaKwasi Evans
Lagos State UniversityNigeriaIsrael Boluwatife Aminu
Laikipia UniversityKenyaMartin Oywa
Larbi Ben M’hidi UniversityAlgeriaSabir Makhkouf
Maasai Mara UniversityKenyaJohn Njeru
Makerere UniversityUgandaJoyce Nabende
Malawi University of Science and TechnologyMalawiChikumbutso Gerson
Mansoura UniversityEgyptMaghfera shrief abdelwahab
Maseno UniversityKenyaJoyce Akinyi Otieno
Masinde Muliro University of Science and TechnologyKenyaKamau Mbugua
Meru University of Science and TechnologyKenyaOmondi Fredrick Adhing’a
Michael Okpara University of AgricultureNigeriaEbeh Elisha
Midlands State UniversityZimbabweBrandon Tinotenda Bande
Moringa SchoolKenyaLynn Njoroge
Multimedia University of KenyaKenyaStephen Kamau
MuzindaHubZimbabweArnod Tinashe Nzira
National College of Information TechnologyMalawiPrecious Nyasulu
National Engineering School of CarthageTunisiaIheb Sliti
National Engineering School Of SousseTunisiaYoussef Fadhloun
National Engineering School of Tunis (ENIT)TunisiaMalek Ammar
National Institute of Applied Science and Technology (INSAT)TunisiaSouha Ben Hassine
National Institute of Posts and Telecommunications RabatMoroccoKamal Addi
National Institute of Statistics and Applied EconomicsMoroccoJabbar Abdelkabir
National University of Science and Technology (NUST)ZimbabweRobert Selemani
Nelson Mandela African Institute of Science and TechnologyTanzaniaMaria Proches Malamsha
Niger Delta UniversityNigeriaAremieye Tamaratombra
Nile UniversityEgyptKarim Amer
Obafemi Awolowo UniversityNigeriaPaul Okewunmi
Olabisi Onabanjo UniversityNigeriaOluwatobi Oluwaseyi Banjo
Redeemer’s UniversityNigeriaAboh Israel
Ruaha Catholic UniversityTanzaniaBaraka Mwendo Oscar
SimplilearnSouth AfricaMduduzi Mcobothi
State University of ZanzibarTanzaniaAbdulmajid Haji Hassan
Strathmore UniversityKenyaAnthony Miyoro
Sudan University of Science and TechnologySudanWafaa Faisal Mukhtar
Technical University of KenyaKenyaGilbert Kunonga
The Catholic University of ZimbabweZimbabweGerald Nchogu
Thies UniversitySenegalMamadou Bousso
Tshwane University of TechnologySouth AfricaDiana Pholo
Université Alioune DIOP de BambeySenegalImam Malick
Université Cheikh Anta Diop de DakarSenegalMendy Gervais
Université de ParakouBeninMarcel Gbaguidi Alia
University Gamal Abdel Nasser de ConakryGuineaAbdoulaye Balde
University Hassan IIMoroccoYassine Labbane
University of AlfashirSudanAlargum Abo Algassim
University of BahriSudanKhalid Osman Elaalim Mohammed
University of Cape TownSouth AfricaSebnem Er
University of DodomaTanzaniaAnthony Mipawa
University of Energy and Natural ResourcesGhanaMichael Holdbrooke
University of GhanaGhanaMark Atta Mensah
University of IbadanNigeriaOdeajo Israel
University of IlorinNigeriaTejumola Asanloko
University of KhartoumSudanMusab Albirair
University of LagosNigeriaVictor Odumuyiwa
University of Malawi – Chancellor CollegeMalawiChisomo Chiweza
University of Malawi PolytechnicMalawiBlessings Mlundira
University of ManoubaTunisiaHoussemeddine Derbel
University of NairobiKenyaWanjiku Nganga
University of Port HarcourtNigeriaGideon Onyewuenyi
University of PretoriaSouth AfricaVukosi Marivate
University of RwandaRwandaJean de Dieu Nyandwi
University of Sol PlaatjeSouth AfricaLebogang Mosetlho
University of South AfricaSouth AfricaKhayelihle Wiseman Biyela
University of StellenboschSouth AfricaWillem Bester
University of Yaounde ICameroonMelatagia Yonta Paulin
University of ZimbabweZimbabweLynn Zigara
Witwatersrand UniversitySouth AfricaBright siKazwe
Zewail City of Science, Technology and InnovationEgyptMazen Ahmed Hassan
Zimbabwe Ezekiel Guti UniversityZimbabweCanisius Ngwenya

You’re invited: find out how to join us at UmojaHack Africa 2021

In 2020, the first UmojaHack Africa drew more than 1000 students from 56 universities and 15 countries across Africa – the biggest inter-university AI hackathon ever hosted in Africa. This year we are going even bigger, hosting a virtual two-day event and hoping to see more than 100 universities join the competition. We are inviting every university in Africa to join in the hackathon on 27-28 March 2021. On the weekend, a network of hackathon events will take place virtually and physically on university campuses across Africa, all linked via livestream and the Zindi platform

Students at each university can compete individually or in teams of up to four people via the Zindi platform. Teams will be representing their universities, and will compete against other universities for more than $10 000 US in prizes for the top student teams as well as for the universities that they represent. Winners will be determined based on the Zindi leaderboard. 

About the Machine Learning Challenges

There will be three machine learning challenges of varying difficulty that speak to uniquely African challenges for students to choose to tackle. Challenges will address issues like gender, conservation, mobility, financial inclusion, and agriculture. Technical content of the challenges may include computer vision, predictive analytics, classification, natural language processing, and GIS data.

At least one challenge will be appropriate for beginners. However, students will need some experience programming in R or Python and will each need their own computer during the hackathon.

Logistics & Organisation

We rely on universities to assist in organisation and logistics on the day, and each university is encouraged to host their own event on the 27-28 March on campus (pandemic conditions allowing). The venue should have reliable internet connectivity, as we will be livestreaming the opening ceremony and prize-giving, as well as for the duration of the event. We will also use live leaderboards on www.zindi.africa to manage and rank submissions.

Universities are encouraged to reach out to sponsors to help cover costs, connectivity and local prize money at their own event – note that Zindi will not be providing prizes for local events.

ProgramME

The tentative programme is as follows (all times are GMT). The hackathon will be a full-day event.

  • Sat 8:00 – 8:45: Welcome and orientation (video conference across all university locations)
  • Sat 8:45 – 9:30: Technical orientation to the problems (video conference across all university locations)
  • Sat 10:00 – Sun 15:00: Students form teams and work on the challenge. Livestream from Zindi HQ continues with interviews with competitors, discussions of the challenges, and other events
  • Sun 15:00 – 15:30: Announcement of winners and prizes (video conference across all university locations)

Prizes

Zindi will offer a total prize pool of $10 000 USD to the top-performing teams and universities, as well as other special prizes. If two teams from the same country place in a prize winning position, only the highest-ranked team and the university they represent will receive prizes in that country. The teams will be judged based on their ranking on the dedicated Zindi leaderboard.

To participate, register your university (note that individuals should not register) at bit.ly/umojahack2021 by 13 March 2021. If you require specific support from Zindi, please register and send an inquiry to us by 28 February. Please direct any questions to Paul Kennedy paul@zindi.africa

Looking back at UmojaHack 2020: 1000 data scientists join hands

On Saturday 22 March 2020, Zindi hosted the first ever pan-African inter-university hackathon, UmojaHack Africa. This groundbreaking event took place in extraordinary circumstances, with the world in the grip of the early stages of the COVID-19 pandemic that has become a feature of everyone’s lives in the alast 12 months.

Nonetheless and in spite of escalating university closures as governments introduced safety precautions to counter the pandemic, students from 56 universities in 15 African countries competed for cash prizes, and seized the opportunity to collaborate and hone their machine learning skills.

The day kicked off with a brief address from Celina Lee, CEO of Zindi, as she welcomed the participants and sponsors to the event. Paul Kennedy, Zindi’s Community Manager, then followed with a recap of the competition rules. As each of the hackathon challenges was a machine learning problem, one of Zindi’s resident data scientists, Jonathan “Johno” Whitaker, took a few minutes to explain the background to each competition. He also provided some useful programming hints and guidelines on how participants could make their first submissions.

There were messages too from our sponsors, including African Bank and Microsoft. Lawrence Muthoga of Microsoft4Afrika was particularly enthused to see Africans working passionately to provide African solutions to African problems.

The diverse challenges on offer exposed competitors to a wide range of data science and machine learning techniques, often for the first time. They included a fire outbreak prediction challenge using data collected in the Democratic Republic of Congo; a challenge to classify marine invertebrates from images taken in South African waters (hosted by SAEON); and finally a challenge to predict customer’s purchasing behaviour for e-commerce customers in Uganda (hosted by Xente). Each challenge was chosen to have wide-reaching potential to make a positive impact within their respective domains while providing a unique challenge for the eager competitors.

And then the day more than 1000 eager students had been waiting for, began! The event was live streamed on YouTube with regular transmissions from the various locations around Africa. At the University of Malawi The Polytechnic, Zindi Ambassador Sam Masikini told us how excited their university was to be participating.

“We’ve being looking forward to UmojaHack Africa for months here, and we’re so grateful to all the groups that have helped to make this possible, especially considering the coronavirus pandemic.”

Sam Masikini, Zindi Ambassador for Malawi

With participants competing from the relative safety of their homes, Upendo Mchome from Tanzania summed up the feelings of the day on Twitter.

“Such a thrill knowing that students from over 70 African universities are working towards the same goal — solving challenges in Africa using Data Science.”

Upendo Mchome

Participants worked tirelessly all day and made just under 2500 submissions across the three challenges. It was especially encouraging to see a significant proportion of women competing, as well as 164 submissions that came from people who were submitting a solution to Zindi for the very first time. After 7.5 hours of hard work, the winners came from Stellenbosch University and the University of Cape Town (UCT) in South Africa, and the Higher School of Communication of Tunis (SUPCOM) in Tunisia. Thanks to sponsors and partners MicrosoftAfrican BankGoogle AIGIZLiquid TelecomAlliance4aiInstadeepThe Field Institute, and Data Science Nigeria, Zindi will distribute almost $20,000 in prizes to winners and their universities.

But it wasn’t only about the cash prizes. As long-time Zindian Lawrence Moruye of Multimedia University of Kenya said, “On Zindi you either win or you learn. There is no lose”, and this was evident in the camaraderie of the students, the buzz and excitement on social media, and messages of gratitude and support that poured in from participants all over Africa.

At a time when communities all over the world face uncertainty and isolation, UmojaHack Africa was a glowing testament to the power of Zindi’s online platform and community, where hundreds of Africans could hold hands and collaborate joyfully across locked borders.

UmojaHack Africa 2021 Schedule

Day 1: Saturday 27 March 2021

YouTube Livestream DAY 1: https://youtu.be/ QOunybIkiLA

07:00 GMT Live stream starts

08:00- 09:00 GMT Welcome, sponsors address and competition launch 

09:00 GMT Competition launch 

10:00-10:30 GMT Q&A with Zindi data scientist (Amy)

12:00-12:30 GMT Chat with NVIDIA + Sendy

14:00-14:15 GMT Chat with Old Mutual

19:00 GMT Live stream close 

Day 2: Sunday 28 March

YouTube Livestream DAY 2: https://youtu.be/G-Z_m3dqUUU

07:00 GMT Live stream starts

08:00-08:15 GMT Welcome back day 2; chat with Standard Bank data science graduates 

08:15-08:30 GMT Q&A with Zindi data scientist (Amy)

10:00-10:15 GMT Live chat with ambassadors

12:00-12:15 GMT Live chat with ambassadors

14:30 GMT Last update (30 minutes to competition close)

15:00 GMT Submission close 

15:30-16:00 GMT Announcement of winners and prizes,competition close

16:00 GMT Live stream close