Nicodème Westphalen

Built an interpretable multiclass model to predict DPE energy labels (A–G) from open ADEME data, with evaluation focused on class imbalance, robustness, and next-step improvements.

A finished team project that turns open French energy data into practical advice on a household's DPE rating. I built the data and prediction side.

Human-Centered research initiative exploring intergenerational disconnection through qualitative inquiry and participatory design.

Exploration of real-time data processing techniques and analysis pipelines for streaming datasets.