↓ Skip to main content
Kwak Jazz

Projects

Projects I build outside of work, to learn something or to answer a question that was nagging me. Source code available for each.

Products

Projects designed to meet a real need (finished or in progress...)

Lab

Projects to learn and master a technology or a concept.

Time series foundation models: forecasting tomorrow's electricity consumption for 3,517 commercial buildings
Lab

Time series foundation models: forecasting tomorrow's electricity consumption for 3,517 commercial buildings

··3412 words
Time Series Forecasting Foundation Models Chronos-2 LightGBM Energy Backtest Conformal Prediction Dagster MLflow Python
The TSFM tech watch applied to a fictional balance responsible party, on real public data: LightGBM, Chronos-2 and their blend against RTE’s day-ahead forecast, published and debiased. A 2.7% MAPE on the portfolio against 5.6% without a model, a router that does not beat the blend, a cold start handled by the naive forecast, Timestral and TimesFM 3.0 in an addendum, a Dagster service and its replayed monitoring.
Causal impact on time series: measuring what a grocery chain's promotions really bring in
Lab

Causal impact on time series: measuring what a grocery chain's promotions really bring in

··2633 words
Causal Inference Time Series Counterfactual BSTS Placebo Tests Double ML Dagster MLflow Python Retail
The BSTS counterfactual from the tech watch applied to the promotions of a fictional grocery chain on the Favorita data: campaigns detected rather than assumed, a donor registry, coverage measured on planted truth (0.83 to 0.90 against 0.5 to 0.7 for iid estimators), the earthquake as a test bench, Double ML, a Dagster pipeline and monitoring.