Prof Audrey Julia Walegwa Mbogho

My research is in the applications of machine learning to problems facing the developing world, and currently I am focusing on education. The questions I am interested in answering are: How can we use machine learning to predict students who are at risk of failure in order to intervene early and avoid that outcome? What sorts of interventions would be most effective? What are the causes of poor performance?

Secondly, in Kenya students, upon completing high school, must choose a course to study at the university with little to no understanding of what that course involves. As a result, many struggle throughout their studies, and yet there is probably a better fitting course that they might chosen and excelled in. It would be interesting to see whether machine learning can be used to recommend a suitable course of study to new students in Kenya.

Audrey was an AfOx-TORCH Fellow in 2019.

During her 8 week AfOx fellowship in 2019, Audrey was hosted by the Department of Geography and Queen's College.

• Mbogho, A., 2017. Using Social Media to Enhance Student Engagement.  In Tien-Chi Huang, V. et al., eds. Emerging Technologies for Education. Springer, pp 320-325.
• Mbogho, A. & Hassanali, J., 2017. Tackling Classroom Apathy among Undergraduate Students in a Developing World Context at Pwani University. In 11th International Technology, Education and Development Conference (INTED17). Valencia, Spain, pp 2337-234
• Mgala, M., Suleman, H., & Mbogho, A., 2016. Undereducation: Motivating Intervention in Rural Schools with MAPPS. In K. Awori, & N. J. Bidwell, eds. Proceedings of the First African Conference on Human Computer Interaction (AfriCHI '16), Nairobi, Kenya. New York: ACM, pp 203-207.
• Mgala, M., & Mbogho, A., 2015. Data-Driven Intervention-Level Prediction Modeling for Academic Performance. Proceedings of the Seventh International Conference on Information and Communication Technologies and Development (ICTD 2015), Singapore. New York: ACM, pp. 2-8.
• Mgala, M., & Mbogho, A., 2014. Selecting Relevant Features for Classifier Optimization. In A. E. Hassanien, et al., eds. Advanced Machine Learning Technologies and Applications. Heidelberg, Germany: Springer, pp. 211-222.