Dunstan Matekenya is a data scientist with nine years of experience blending statistics, geospatial analysis, and machine learning to solve real-world problems across government, academia, and international development. Trained as a mathematician and statistician, he led large-scale national surveys and managed GIS operations before pivoting to applied ML for his PhD—where he built a Hadoop/Spark pipeline and predictive models on cellular mobility data. At the World Bank he applies text, graph, network and satellite-image analytics to inform urban planning, disaster response, and poverty estimation, and has hands-on experience deploying CNNs/RNNs for image and sequence tasks. He’s comfortable moving from sampling theory and hypothesis testing to production ML, with a habit of interrogating algorithms’ theory and proposing principled enhancements. Based in Washington, D.C., he combines a deep academic grounding with practical engineering skills in Python, Java, Hadoop, and Spark to turn complex spatial-temporal datasets into actionable insights.
9 years of coding experience
10 years of employment as a software developer
University of Tokyo
Bachelor of Education (B.Ed.), Mathematics, Bachelor of Education (B.Ed.), Mathematics at University of Malawi
Master of Science (MSc), Geospatial Information Science, Master of Science (MSc), Geospatial Information Science at Curtin University
Contributions:4 commits, 5 pushes, 1 branch in 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.