Multi-Object Tracking for Passenger Counting
A real-world MOT benchmark from live Lagos bus footage, with failure forensics driving targeted engineering fixes. My current M.Sc. research at NITech.
A fuller selection of my work across data science, machine learning, computer vision and business intelligence, from research prototypes to production dashboards.
A real-world MOT benchmark from live Lagos bus footage, with failure forensics driving targeted engineering fixes. My current M.Sc. research at NITech.
A real-time line-crossing and polygon counting pipeline that surfaced ID-switching as the main source of overcounting, the finding that motivated the research above.

A GPT + LangChain interface over LAMATA operations data, letting non-technical staff query KPIs in plain language, no SQL required.
A model ranking optimal electric Bus Rapid Transit corridors in Lagos from congestion, land-use, density and accessibility data.

A hybrid ML + deep-learning classifier for brand-reputation and customer-feedback monitoring with strong real-world accuracy.

A simulation framework forecasting Microsoft (MSFT) prices with probabilistic risk bands to support investment decisions.

A Power BI dashboard surfacing live ridership, revenue and service KPIs across LAMATA operations.
Real-time PM2.5 analysis from Lagos’ first statewide monitoring network, translating sensor data into policy insight for the EPIC UChicago fund.
An AI SQL agent (Miksi) answering natural-language questions over relational databases with a custom forecast function.

A dynamic report presenting income statements, balance sheets and cash flow with drill-through for executive reporting.

An interactive P&L with variance analysis, budget-vs-actual comparison and time-intelligence for month-over-month insight.

Advanced Python visualisations uncovering patterns, correlations and anomalies across complex multi-variable datasets.