Blog
Notes on data science and machine learning.
Practical write-ups on modelling, evaluation, MLOps, and the work around the model.
Baselines before deep learning
Why the first model I build is almost always the simplest one, and how it keeps every later improvement honest.
Monitoring models in production
A model is only finished when you can tell it is still working. The few checks I set up before every launch.
Evaluating forecasts honestly
A single train/test split flatters time-series models. Rolling backtests give a number you can trust.