Logistics · operations

Forecasting that survived contact with reality.

How a logistics operator stopped shipping notebook-perfect forecasts that broke in week one — and built a demand system the ops team trusts enough to overrule.

[ figure 1 — backtest vs. live, twelve weeks ]
-22%
forecast error
-60%
on-call pages
12 wks
baseline held
100%
overridable by ops

The models were beautiful in the notebook and brittle in the world. Each new demand forecast looked like a step change in accuracy right up until the week it shipped, when a holiday, a promotion, or a weather event it had never seen would send it sideways — and the ops team would quietly go back to their spreadsheet.

The problem, precisely

The failure wasn’t the model; it was the absence of everything around the model. No honest backtest, no drift detection, no way for the people who actually run operations to say “not this week.” A forecast the team can’t override is a forecast the team learns to ignore.

The approach

We started by building the least glamorous thing in the project: a boring baseline nobody was allowed to beat without proving it on a real backtest. Then drift monitoring to catch the model wandering, and an override workflow so ops stayed in command.

A model your operators can veto is a model your operators will actually use.

What we built

# forecasting loop
baseline  →  deliberately boring, hard to beat
backtest  →  honest replay on unseen periods
serve     →  forecast + confidence band
monitor   →  drift + error alerts, not silent decay
override  →  ops can veto, with the reason logged

How we knew it worked

The baseline held for twelve weeks before any model earned its way past it — which was the point. When the learned model finally shipped, forecast error dropped 22%, on-call pages fell 60%, and every forecast stayed overridable by the ops team, with each veto logged as training signal for the next round.

// the implementation book

Shipping Forecasts That Hold

The backtesting harness, the drift monitors, the deliberately boring baseline, and the override workflow — everything needed to ship a forecasting system that survives the week it meets production.

Have a problem shaped like this one?