I’m a Junior Data Scientist with a strong foundation in business intelligence and a growing focus on machine learning for real-world forecasting and decision systems. My work sits at the intersection of retail operations and applied AI — using data to improve planning, efficiency, and business impact.

🏢 Currently: Junior Data Scientist @ Rossmann Polska
⚙️ Working on: forecasting & analytics pipelines (Python · Pandas · scikit-learn · Qlik Sense)
💡 Focus: data quality, feature engineering & machine learning foundations
🚀 Currently deepening: Git workflow & ML pipeline automation
🧠 Philosophy: “Less noise, more signal — data science that drives decisions.”

💡 Core: Python · Pandas · NumPy · scikit-learn · SQL · Qlik Sense
📚 Currently Learning: XGBoost · Time Series Forecasting · FastAPI · Streamlit · GitHub Actions
🚀 Exploring Next: RAPIDS (GPU Computing) · Optuna · Docker

GPU Forecast Platform (MVP) — GPU-accelerated demand forecasting engine (XGBoost / RAPIDS).
→ Benchmarks CPU vs GPU performance, deploys forecasts via FastAPI.
🔗 Repo · Demo

Retail EDA Toolkit — plug-and-play EDA framework for retail datasets.
→ Simplifies feature discovery, trend analysis, and KPI visualization.
🔗 Repo

FPL333 Analytics — real-time Fantasy Premier League dashboard.
→ Tracks scores, transfers, and standings with automated updates.
🔗 Repo · Live

I love exploring and visualizing data — from raw EDA to model explainability and forecasts. Here are some selected visuals from my recent projects.

Practical machine learning foundations through hands-on mini projects

• 🧮 Feature Engineering for Time Series: lags, rolling stats, calendar patterns
• 🔧 Model Deployment: Streamlit dashboards & FastAPI endpoints
• 🧰 Automation: CI/CD and version control for reproducible ML repos
• 📈 Interpretability: SHAP, feature importance, partial dependence plots