This article was first published by Ms. Neema Mduma https://neylicious.github.io/ml/2019/05/11/paper.html – Neema is an alumni of the CODATA-RDA School of Research Data Science.

In early 2017, I was privileged to work as a researcher in the Dropwall project (by Rose Funja) which was among the winning project of the Data for Local Impact Innovation Challenge (DLIIC). The main focus of the project was to develop a tool that will help fighting dropout among secondary school girls. The findings from this project show a high rate of dropout among secondary school students particularly girls, and coincide with reports from other studies which show that school dropout is a big challenge in developing countries. On addressing this problem, machine learning techniques has gained much attention in recent years. However, most of the work has been carried out in developed countries, there are only a handful of studies conducted in developing countries on school dropout using machine learning techniques with the consideration of local context and data imbalance problem. This motivated me to continue working (in my PhD) on school dropout using machine learning.

In August 2018, I attended a CODATA-RDA Research Data Science Summer School which was held at the Abdus Salam International Centre of Theoretical Physics (ICTP) in Trieste, Italy. The aim was on building competence in data analysis and security for participants from all disciplines and backgrounds from Sciences to Humanities. The level of engagements and interactions between participants and instructors was outstanding. We were introduced to various opportunities (by The Executive Director of CODATA, Dr. Simon Hodson) such as CODATA Data Science Journal where I later managed to publish the breathtaking findings from the Dropwall project titled A Survey of Machine Learning Approaches and Techniques for Student Dropout Prediction.