Skill in Machine learning, MLOps

Model evaluation

Measuring whether a model is good enough, offline and online.

2 books

Time Series Forecasting

How to forecast demand a day ahead and check that the forecast holds up: baselines, backtests that never see the future, statistical models, one LightGBM model for all clients, totals that add up, and calibrated prediction intervals, on hourly electricity demand from thirty clients.

Edition 2026.11.11 · Examples passed Nov 20, 2026 · 41 of 41 examples pass

Small Open Models

How to replace a hosted model with one you run for a single job, and when it is the wrong choice: measuring the task, choosing a base model, prompting, LoRA fine-tuning, distillation, quantization, CPU serving, versions and hand-offs to people, on a bank's support messages from BANKING77.

Edition 2026.11.9 · Examples passed Nov 20, 2026 · 36 of 36 examples pass