Examples of some my published work can be found on Kaggle, where I maintain a selection of my notebooks, I am also author of "The Orange Book of Machine Learning". Previously I worked as an academic researcher in the field of statistical mechanics and thermodynamics, and a list of the over 40 publications that I have co-authored can be found on my home page (h-index=24).
My primary skills are:
- data exploration and experimentation
- predictive modelling of tabular / structured data using the tools of machine learning
- proof of concept (PoC) prototype models
- regression techniques with conformal prediction intervals
- well calibrated probabilistic classification
If you wish to get in touch it would be a pleasure to connect on LinkedIn.
Needless to say a great deal of what I do is made possible by the groundwork of others, and the vast majority of the source of the python packages can be found right here on GitHub, for example:
- NumPy / SciPy
- pandas / polars
- statsmodels
- scikit-learn
- XGBoost / CatBoost / LightGBM
- quantile-forest and MAPIE
- TabPFN by Prior Labs
- Matplotlib / plotly / seaborn along with missingno
all facilitated from within the JupyterLab computational environment.