UP graduate and mathematical statistician wins silver medal in global Kaggle competition for research prediction

Posted on December 02, 2020

Dr Hossein Masoumi Karakani, who was awarded a PhD in Mathematical Statistics by the University of Pretoria (UP) in 2020, recently finished 129th out of 2 618 teams (including single-member “teams”, like Dr Karakani’s) registered globally when he took part in a Kaggle competition. He ended in the top 5% and won a silver medal.

Kaggle is the world’s largest data science community and the most well-known competition platform for predictive modelling and data analytics, with at least one million registered users across the globe. It was founded in Melbourne, Australia, in 2010 and was acquired by Google in 2017. This particular Research Prediction Competition was hosted by Kaggle in collaboration with the University of Liverpool’s Institute of Ageing and Chronic Disease, and Dr Karakani became the first person from UP’s Department of Statistics to win a medal in a Kaggle competition.

Competitors were provided with electric signals corresponding to ion channel data and were required to create an algorithm that could automatically identify the number of open channels at each time point. Ion channels are pore-forming proteins that are present in animals and plants and encode learning and memory, help fight infections, enable pain signals and stimulate muscle contractions.

When asked how he felt about this achievement, Dr Karakani commented: “Receiving this prestigious award was a massive achievement. Rubbing shoulders with some of the smartest data scientists in the world will surely be a life-changing experience, especially for a young statistician like me. This competition showed me that I can make my mark in the hugely competitive world out there. Educational background plays a significant role in becoming a successful data scientist. During my time in the Department of Statistics, I mastered the art of programming and realised the importance of well-structured and documented code in applied statistics and real-world data science projects. Through hard work and determination I succeeded in honing my skills to become a successful statistician.”

Dr Karakani, who completed a BSc degree at the Allameh Tabataba’i University in Iran and an MSc at the UP, is a knowledgeable statistician with teaching and research experience. As a data scientist at Knowledge Integration Dynamics (KID), he is currently involved in predictive analytics projects and plays a key role in delivering insights and implementing action-oriented solutions to complex business and technology problems.

His advice to would-be statisticians was: “The decision to become a data scientist is similar to choosing a delicious starter from among a plethora of options in a restaurant. For anyone who dreams of a career in this field, I recommend the following: Get your fundamentals strong enough by mastering the theory; master statistics and probability – the bread and butter of the data science realm – participate in competitions to learn and  pick up new skills, and make your GitHub profile alive and complete with end-to-end implementation, including documentation.”

- Author Martie Meyer
Published by Hlengiwe Mnguni

Copyright © University of Pretoria 2021. All rights reserved.

FAQ's Email Us Virtual Campus Share Cookie Preferences