
01
Loan Default ML Pipeline
Turning 148,670 loan records into a calibrated lending decision, and throwing away the first model because it was perfect.
2026Case study →
Work
Four case studies, each written like a story rather than a README, followed by the rest of the shelf.
(01) — Case studies

01
Turning 148,670 loan records into a calibrated lending decision, and throwing away the first model because it was perfect.
2026Case study →
solar-powered purification02
A solar-powered water purification system for communities where the grid is unreliable and the water is not safe.
2025Case study →

03
A Nigerian tax assistant that does the arithmetic deterministically and lets the language model do only what it is good at: reading.
2026Case study →

04
Not a pitch competition. A nine-stage entrepreneurship pipeline built from scratch at a university in Northwestern Nigeria.
2026Case study →
(02) — More work
Smaller builds, analyses and the organisations I have started or helped run.
012025
Scholarship discovery with a Selenium scraper, FastAPI backend and a weighted recommender. React and TypeScript on the front.
↗
022026
OLS elasticity, Granger causality, GARCH volatility and a trade-finance gap estimate across 2010–2024, written up as a policy report.
↗
032026
A scored benchmark of entropy sources, from a biased generator to real quantum bytes from the ANU QRNG.
↗
042026
A NumPy simulation of a photonic network with Mach-Zehnder interferometers, trained by finite differences on MNIST.
↗
05Ongoing
Founded and lead a tech-focused student innovation club: training, competitions, an annual exhibition and incubation support for early ideas.

062025
As Business Development Officer: skills workshops, an Entrepreneurship Lab, and a trade fair with 1,500+ students. Named a top-five campus organisation.
072025 –
Co-founded a last-mile delivery venture for Northern Nigeria. MVP built, pilot running.