~/projects
Projects
Each entry links to a case study with architecture, measured results, limitations and the exact commands to run it yourself.
2 / 2
Machine Learning2026 · complete
SIWES Oil Spill Risk Classifier
Severity classifier for Niger Delta oil spills built on NOSDRA incident records. Three XGBoost setups were compared on a 96%-Minor dataset; class weighting won on macro F1 and minority recall, at a large cost in precision.
Pythonpandasscikit-learnXGBoostGridSearchCV
read case study →NLP2026 · complete
Smart Resume Screener
Local-first ATS that ranks resumes against a job description using Ollama embeddings and a five-signal scoring model. No API keys, no data leaves the machine.
PythonFastAPIOllamanomic-embed-textllama3.2:1b
read case study →