Tutorials, real-world projects, datasets and research — all in one connected knowledge platform. From first principles to production systems.
With the fastest-growing young population, increasing mobile penetration and a wealth of underexplored problems, sub-Saharan Africa presents a unique and urgent opportunity for machine learning researchers. Here is what the data says.
A practical guide to Pandas — the most important library in any data scientist's toolkit. We cover Series, DataFrames, loc/iloc, merging and aggregation.
Build linear regression step by step using only NumPy. Understand gradient descent, the loss surface and how libraries like scikit-learn do it under the hood.
A reproducible EDA workflow covering distributions, correlations, outliers and business context — the foundation of every good ML project.
A complete end-to-end ML case study for a telecom company. From raw data to a deployed API, covering EDA, feature engineering, model selection, cross-validation, hyperparameter tuning and business impact analysis.
Chapters
A visual explanation of attention — the core idea behind every modern language model.
Target leakage, wrong splitting strategies and other errors that make models look better than they are.
We develop a multi-modal ML model combining MODIS satellite data with weather station readings to predict maize yield 60 days before harvest.
Analysis of anomaly detection techniques applied to mobile money transaction logs across East African networks.
GDP, inflation, FDI, trade balance and population data for all 54 African countries across 25 years. Sourced from the African Development Bank and World Bank.
Python → NumPy → Pandas → Statistics → ML → Deep Learning → Deployment
SQL → Python → EDA → Visualization → Statistics → Reporting
Mathematics → ML Theory → Deep Learning → Research Methods → Publishing
New tutorials, research findings, datasets and project walkthroughs, delivered to your inbox. No spam. Unsubscribe any time.