Quantile forecasts across horizons

Model choice is a property of the data, horizon and loss function. This article uses quantile forecasts across horizons to highlight those design choices and their consequences.

Practitioner lens

Forecast distributions from quantile forecasts across horizons become actionable when passed into inventory, sourcing or capacity models. Preserving uncertainty is often more useful than collapsing it too early.

First experiment

Use rolling-origin backtests, horizon-specific losses and interval coverage; keep feature availability time-correct.

This is an original educational brief. It is a starting point for discussion, not a claim that one technique fits every supply chain.