Short-term forecast

As explained in Demand Forecasting Best Practices

Short-term forecasting predicts demand over a relatively near future horizon.

A short-term forecast predicts demand over the near future to support immediate supply-chain decisions. Its value depends on matching the horizon and detail to the decision: shipping may require SKU-per-store forecasts for the next few weeks, while production or finance needs broader, longer views. section 7.1 section 1.3

Use short-term forecasts as decision information rather than as a frozen version of the supply plan:

• Update forecasts regularly, even when supply plans are temporarily frozen; revised demand can improve mid-term planning. section 6.2
• Keep every near-term period relevant to the current order: changing the M2 forecast from 75 to 100 pieces increases the order by 25 units in the example. section 6.2
• Prefer granular information such as product, store, and day when teams use the forecast for near-term shipping decisions. section 7.1
• Limit review effort to forecasts and products where planners are most likely to add value, using forecast value added to track interventions. section 1.2.5

Weekly store replenishment

Suppose a retailer decides each week what to ship to its stores. A short-term forecast can be updated weekly for a few weeks ahead at SKU-per-store granularity. Because review time is limited, a small group of demand planners validates only the products where human input is most likely to improve the baseline. section 1.2.5

Figure 7.1 Supply chain roles and forecasting granularities and horizons

Compare how supply-chain roles require different forecasting horizons and granularities. section 7.1

How Demand Forecasting Best Practices covers it

How deep it goes

Defines horizon and granularity, demonstrates order effects, and outlines review practices without detailing forecasting algorithms.

Examples

Uses weekly store shipments, SKU-per-store forecasts, and a 25-unit order increase after revising M2 demand.

What it assumes

Assumes demand-planning and supply-planning context while emphasizing objectives, data, metrics, baseline models, and review.

What you can do after

Apply it by aligning forecast updates, granularity, and review effort with near-term supply-chain decisions.

How it connects

Connects demand planning with supply planning, forecast value added, inventory decisions, and machine learning models.

liveBookmanning.com

Read Demand Forecasting Best Practices on liveBook Get the book at manning.com

Related concepts

• granularityuses · Granularity is the level of detail or fineness at which information, behavior, or a system is represented, grouped, or divided.
• production and supply plansused by · Production and supply plans are coordinated plans for producing, sourcing, and supplying the quantities of goods needed over time.
• language modelused by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.

This explainer was generated by Manning's knowledge graph from the text of Demand Forecasting Best Practices. The section links point to the parts of the book it draws on.