I go where the
data lives.
Six years turning satellite passes, farmer surveys, and causal inference into models that East African governments and international partners act on — from the vanilla farms of the west to a presentation at the national policy table.
- Field years
- 6+
- Projects delivered
- 15+
- Pipeline data quality
- 95%+
Past Engagements
Shaped by Research. Defined by the Mathematics.
I started my career in management consulting at Bronkar Uganda — learning how organisations frame decisions and what makes evidence actually move people. That curiosity pulled me deeper: I moved into M&E research for international non-profits, running evaluations and impact assessments for USAID, UNDP, IRC, and others across East Africa.
The more rigorous the questions got, the more I wanted the mathematical tools to match them. That's what drove me to the M.Sc. in Data Science — not a pivot, a deliberate deepening. I wanted to work across the full stack: machine learning, natural language processing, computer vision, and Bayesian statistical inference — not just apply packaged methods, but understand what's happening inside them.
That depth has shaped the systems I've built since: a predictive analytics platform for Uganda's vanilla export sector at MAAIF and Makerere University, fusing NASA POWER satellite data with ground measurements to cut forecast error by 18% — findings that reached a national forum attended by the Head of State. And automated evaluation pipelines at USAID SITES that compressed six-week assessment cycles to under ten days.
Today I work two roles remotely: Research & MEAL Specialist at the Center for Research & Communication, and R&D Consultant at Enimiro, where I build the farmer data system, yield models, and plot maps behind a vanilla and coffee agribusiness. I'm drawn to problems where the uncertainty is real, the data is difficult, and getting it right actually changes something. Certified in Power BI, SAS, Tableau, and Google project management. Based in Kampala — open to remote and international engagements.
Depth
ML · NLP · Computer Vision · Bayesian Inference — across the full stack, from statistical foundations through production deployment.
Impact
18% forecast error reduction. 85% faster evaluation cycles. Evidence that reached Uganda's national policy table and shaped real programme decisions.
Recognition
Co-author on peer-reviewed agronomy research in Agronomy (MDPI) and Advances in Agriculture (Wiley), and presented findings at a national forum attended by President Museveni.
Experience
-
Nov 2025 — Present
Research & Data Consultant
Enimiro · RemoteOwn the data platform behind a vanilla and coffee agribusiness: seven automated pipelines spanning SurveyCTO-to-PostgreSQL ETL, NASA POWER climate data, Prophet harvest forecasts, purchase and pollination analysis, and inspection follow-ups. Also lead standalone studies, including a farmer Living Income study and the Kayunga agrohub needs assessment, plus a yield-estimation model and district plot maps.
-
Jan 2025 — Present
Research & MEAL Specialist
Center for Research & Communication (CRC)Lead analytics, AI adoption, and M&E frameworks across multi-sector programmes. Run technical workshops on ML, statistical modelling, Python, R, and Power BI, and establish data-governance and quality-assurance protocols.
-
Jan 2024 — May 2025
Data Scientist
MAAIF · VANEX · Makerere University · CRSBuilt an end-to-end forecasting system fusing API, satellite, and ground data (18% MAE reduction, 80%+ accuracy), automated ETL pipelines with Python and Airflow, and presented findings to a national forum attended by the Head of State.
-
Jun 2023 — May 2025
Research Associate
USAID-SITES · SSS Inc. · DLH CorporationSupervised digital data collection and ran SQL/Python data-quality audits (95%+ reliability) for facility readiness and Health Information Exchange assessments, with stakeholder dashboards and automated reporting across SurveyCTO, Power BI, and PostgreSQL.
-
Jul 2021 — Jun 2023
Data Analyst / Research Associate
Bronkar (U) LimitedDesigned M&E frameworks and digital data-collection tools that cut field operations time by 25%, ran mixed-methods statistical analysis, and led staff training on analytics tools across East Africa.
Featured Projects
Vanilla Supply Chain Predictive Analytics
Forecasting system fusing NASA POWER satellite data, ground measurements, and market prices. Cut forecast MAE by 18%; findings presented to MAAIF at the national workshop.
Automated Impact Evaluation Pipeline
Python + Airflow pipeline covering ingestion, causal inference modelling, and report generation. Evaluation cycles went from 6 weeks to under 10 days.
Advanced Time-Series Forecasting
Hierarchical time-series forecasting with Prophet and ARIMA for Ugandan vanilla yields — the method behind the 30% accuracy gain presented at the national forum.
Health Data Quality & HIE Readiness
With USAID/SITES and the Ministry of Health, ran facility readiness assessments for the transition to Health Information Exchange and built data-quality audits across health facilities in the Lango, Kigezi, and Busoga regions.
Social-Media Sentiment & Information Flow
MSc Data Science capstone at MAHE: sentiment analysis of social-media posts, plus a network model of users as nodes and their interactions as edges, to study how information spreads across the graph.
Gesture & Object Recognition
MSc Data Science capstone at MAHE: machine perception for robotics — interpreting hand gestures (such as a thumbs-up) and recognising objects from a camera feed, so a machine can read its surroundings.
Vanilla Yield Estimation Model
Random-forest model predicting recorded harvest for 275 surveyed farmers, validated out-of-fold. Beats the median baseline by cutting MAE from 158 to 101 kg; certification status, land size, and plant count carry the most signal.
Farm Data & Analytics Platform
Seven scheduled pipelines on one platform: SurveyCTO-to-PostgreSQL ETL, NASA POWER climate scraping, Prophet harvest forecasts, purchase-loyalty analysis, pollination monitoring, and inspection follow-ups, feeding Power BI and Looker dashboards.
Farmer Plot Geomapping
Turned GPS plot boundaries into interactive district maps for agrohub planning across Kayunga, Rubirizi, and other districts — static grids for print and browsable HTML maps of farmer plots for field teams.
Vanilla Farmer Living Income Study
Measured the gap between vanilla farmer earnings and a living-income benchmark, using Anker and Fairtrade reference values. A modular Python/R pipeline cleaned 485 survey columns into an analysis-ready dataset and a written study.
Kayunga Agrohub Needs Assessment
Designed and analysed a farmer needs assessment for a planned agrohub in Kayunga, covering who was surveyed, vanilla production, income, and top challenges, written up as a decision-ready report for management.
Live Analytics
Transaction Fraud Detection Model
Gradient-boosted risk scores across 2,000 synthetic bank transactions. Each point is plotted by predicted risk score vs. transaction amount (log scale); the clustering reveals how the model separates legitimate behaviour from suspicious and confirmed fraud. The dashed vertical line marks the 0.50 classification threshold.
Skills & Technologies
Programming & Data Science
Analytics & Engineering
Let's talk about a project
If you're weighing a data problem where the uncertainty is real and the stakes are concrete — an evaluation, a forecast, a model that has to hold up in the field — I'd like to hear about it. Based in Kampala; I work with partners across East Africa and remotely worldwide.
Scan to connect
Testimonials
"Johnson's forecasts changed how we plan. He combined satellite data with our field measurements, and the results went straight into briefings at the highest levels of government."
"The pipeline Johnson built took our evaluation process from six weeks to under ten days. Our USAID reports now go out on schedule, with data we don't have to re-check."
"Few people can build the model and then explain it to a policymaker. Johnson's research was presented at the highest level of government, and it held up."
Publications & Key Presentations
Unravelling Yield and Yield-Related Traits in Soybean Using GGE Biplot and Path Analysis
Agronomy (MDPI) · 2024 · Vol. 14, Art. 2826 · Open access
Co-authored study evaluating the yield and stability of 12 elite soybean varieties across five production areas in Uganda, using GGE biplot and path analysis to identify traits that improve yield in tropical breeding programmes.
Identifying Optimal Lines for Enhanced Symbiotic Performance in a Mini-Core Collection of Cowpea
Advances in Agriculture (Wiley) · 2025 · Open access
Co-authored study screening a mini-core cowpea collection for nitrogen-fixation and symbiotic performance, applying statistical analysis to select superior genotypes for field evaluation across Ugandan agro-ecologies.
Presidential Presentation on Agricultural Analytics
Presented to H.E. President Yoweri Kaguta Museveni · April 2025 · Makerere University
Presented vanilla supply-chain forecasting research at the national forum: ML models fusing satellite and ground data, a 30% gain in forecast accuracy, and specific recommendations for agricultural policy.
Impact Evaluation Methodologies Workshop
CRC Studies · 2025 · Multiple Stakeholder Sessions
Ran technical workshops for programme evaluation teams across East Africa: statistical modelling, causal inference, and how to automate the analysis they were doing by hand.
Education & Certifications
Education