Peer-reviewed research reports, datasets and experiments focused on machine learning applications in African contexts. All reports are freely downloadable.
We develop a multi-modal ML model combining MODIS satellite data with weather station readings to predict maize yield 60 days before harvest. Tested across Kenya, Tanzania and Ethiopia.
Analysis of anomaly detection techniques applied to mobile money transaction logs across East African networks. We benchmark 7 algorithms and propose a novel ensemble approach.
A survey and benchmarking of NLP techniques for Swahili, Yoruba and Amharic, with new datasets and baseline models released publicly.