In production
S&OP: one number, many calendars
Sales and operations planning wants a number the company can staff, buy, and book against. It fails when each function brings a private forecast. The work is not a prettier chart. It is one grain, one horizon per decision, and a cadence that matches the meeting.
Updated Aug 26, 2026·8 min read
One number is a treaty
Sales and operations planning wants a number the company can staff, buy, and book against. It fails when each function brings a private forecast. The work is not a prettier chart. It is one grain, one horizon per decision, and a cadence that matches the meeting — plus the honesty to keep a statistical path underneath the treaty.
Monthly is not daily
Replenishment is short and fine. S&OP is slower and aggregated. Stretching one model across both is how the monthly consensus becomes a daily lie. Reconcile. Do not pretend. Hierarchical forecasting is the peace treaty between those clocks.
- Name the noun: units, hours, dollars — mixed units are how meetings never end.
- Bias is the political metric. Show it next to WAPE. A systematic +8% is a process.
- Overrides belong in an FVA table, not in folklore.
Bias is the political metric
Sales forecasts high. Ops forecasts low. Finance splits the difference and calls it consensus. Measure it. If you only report accuracy, the game will continue. Predict.ai will not stop the game. It will put the statistical path on the table so the split is a choice, not a mystery.
A live system under the meeting
Keep the S&OP number as a Predict.ai goal with a weekly or monthly horizon, and the operational path as another. Driver discovery and the tournament still run between meetings, so you are not rebuilding the forecast from scratch every 30 days. Export the pinned path into the planning tool. Argue about the treaty, not about whose CSV is newer.
FAQ
- Should S&OP use the same forecast as replenishment?
- Same data, different products. Replenishment is short and fine. S&OP is slower and aggregated. Reconcile them. Do not pretend they are one path.
- What if sales always forecasts high?
- That is bias, and it is measurable. Show percent bias next to WAPE. A systematic +8% is a process, not an opinion you debate every month from scratch.
Keep going
Guide
Forecast value added
Forecast value added (FVA) asks whether each layer — the naive, the model, the planner’s override — actually reduced error. If the override makes WAPE worse, the meeting is a cost center, not a control tower.
Guide
Hierarchical forecasting
You rarely forecast one series. You forecast stores that must sum to a region, and SKUs that must sum to a brand. Hierarchical forecasting predicts at more than one grain and reconciles so finance and ops are not holding two official numbers.
Guide
FP&A forecasting
Finance needs a slower, cleaner number than a warehouse. The mistake is either ignoring the operational forecast or forcing it into a 12-month line that cannot be true. FP&A should consume a reconciled path, plus scenarios, plus an interval.
Use case
Production output forecasting
Forecast finished output from schedule, staffing, material availability, cycle time, downtime, and yield.
Use case
Shipment volume forecasting
Forecast inbound and outbound volume by lane, facility, customer, and mode before capacity is committed.