Operators, product owners, and people affected by the forecasting decision.
Forecasting & temporal ML
Regional demand shifts through promotions, holidays, and drift.
A measurable problem, before a model.
forecast origin, seasonal naive, lag features, rolling backtests with version, owner, event time, and availability contracts.
Regional demand shifts through promotions, holidays, and drift. Every solution must state latency, cost, capacity, and fallback limits.
Offline evidence plus a deployable resolution: Rolling validation, statistical baselines, boosted forecasts, and uncertainty bands.
Frame and baseline
Turn the production problem into explicit data, metric, and baseline contracts.
- 01↗
Forecast contracts and naive models
A forecast begins with two clocks—when you know and when you predict—and a baseline that respects both.
65–90 min · checkpoint · deterministic lab - 02↗
Trend, seasonality, and known-future signals
A temporal feature is valid only if its value could be reconstructed exactly at the forecast origin.
65–90 min · checkpoint · deterministic lab
Build and stress
Formalize the machinery, test counterexamples, and expose system limits.
- 03↗
Backtesting without time travel
A faithful backtest is a replay of past information states, not merely a sorted split.
65–90 min · checkpoint · deterministic lab - 04↗
Statistical and ML forecasters
Choose a forecaster and a multi-step strategy together; the estimator alone does not define the forecast.
65–90 min · checkpoint · deterministic lab
Resolve and operate
Join model behavior to architecture, observability, rollout, and rollback.
- 05↗
Intervals, drift, and forecast operations
Forecast reliability is the joint discipline of calibrated ranges, drift evidence, and a usable fallback.
65–90 min · checkpoint · deterministic lab - HW↗
Regional demand forecast
Build a 24-hour pipeline with naive, statistical, and boosted baselines plus interval forecasts.
Rubric · staged hints · reference resolution
3 concepts make this faster.
Prerequisites are guidance, never hard gates.