20+ years of experience modelling complex, noisy systems — originally in astrophysics, now applied to commercial data science and machine learning problems. My work focuses on machine learning, statistical inference and time series analysis, with an emphasis on extracting signal from difficult datasets and supporting decision-making under uncertainty.

📍 Athens, Greece · Open to remote, hybrid and on-site roles across Europe & the UK

Machine Learning

• Classification
• Regression
• Neural Networks

Statistics

• A/B Testing
• Confidence Intervals
• Hypothesis Testing

Forecasting

• ARIMA
• Holt-Winters
• Prophet

Core Stack

• Python
• SQL
• Git
• C
• IDL
• Unix shell

• Battery Health ML Workbench

  End-to-end battery prognostics from 1.6M observations, with Leave-One-Group-Out validation on independent trajectories

• Fraud Detection (ML)

  Supervised models for rare-event detection in highly imbalanced data, with threshold optimisation for real-world alerting trade-offs

• Clustering & Segmentation Workbench

  Interactive unsupervised learning app: hierarchical clustering, K-means, PCA, with WCSS/silhouette diagnostics

• SQL to Pandas Toolkit

  Interactive translator between SQL operations (joins, window functions, GROUP BY) and pandas equivalents

• A/B Testing Toolkit

  Reusable tools for comparing groups using confidence intervals and hypothesis testing

• Time Series Forecasting Toolkit

  Interactive framework comparing ARIMA, Holt-Winters and Prophet, with backtesting and error analysis

• scorner

  Published, pip-installable Python package for multi-dimensional data visualisation

• Dashboards (Tableau / Plotly Dash)

  • Logistics performance
  • UK unemployment trends
  • NZ greenhouse gas emissions

Python (pandas, NumPy, scikit-learn, TensorFlow) · SQL · Statistical Modelling · Machine Learning · Time Series Forecasting · Hypothesis Testing · Data Visualisation (Plotly, Tableau, matplotlib) · Git