I build things that ship: Elexon BMRS forecasting pipelines, local-LLM phone systems, and production web platforms. BSc Computer Engineering, 1st in class (GPA 18.87/20). Enterprise Scholarship. Student Rep Gold Award. Currently wrapping up MSc Data Science at UWE Bristol.
| Project | What it does | Stack | Status |
|---|---|---|---|
| GB Balancing Mechanism Forecasting | Forecasting total GB balancing mechanism cost per settlement period, a target no published GB study models directly. LEAR baseline vs XGBoost and LSTM, rolling-window evaluation, Diebold-Mariano testing | Python · XGBoost · LSTM | 🔵 Due Jan 2027 |
| Reception System | Local LLM phone handler for SMEs, prototype stage: Whisper STT, fine-tuned LLaMA/Phi-3, Google Calendar API | Python · FastAPI · Ollama | 🟡 Prototype |
| SmartQuote Assistant | Email extraction + quote reply automation, 96% field accuracy | Python · Ollama · OpenAI | ✅ Done |
| Whisper STT Eval | STT evaluation on LibriSpeech: WER, CER, latency + live Streamlit dashboard | Python · Faster-Whisper | ✅ Done |
| ML Practice | One algorithm per week: theory notes + notebook, KNN to MLP | Python · scikit-learn | 🟢 Active |
| Crime & Deprivation | Crime vs deprivation across English police areas | MongoDB · PostgreSQL | ✅ Done |
| Retail KPI Pipeline | End-to-end BI pipeline over £10.6M sales dataset. ETL, MySQL, Streamlit | Python · Pandas · MySQL | ✅ Done |
| File Organizer | Python CLI that auto-sorts files by type, with dry-run, undo, custom config | Python | ✅ Done |
Languages
Data & ML
Currently learning
Databases & Infrastructure
Bristol, UK · Open to internships and graduate roles · knhnf.github.io