Demand Forecasting

StockrHub’s forecasting engine uses sold order history to plan what should be stocked, what can stay vendor-backed, and where limited purchasing budget should go first.

What It Uses

The forecasting workflow is intentionally narrow:

• sold Shopify order line items only
• up to 24 months of history
• current owned inventory
• incoming open purchase orders
• supplier lead times
• supplier-backed stock coverage where available

It does not pull the full product catalog just to forecast demand.

How Forecasting Works

1. Sync sold order history from Shopify in bounded steps.
2. Store reusable sales facts in Stockr so the page can load quickly without re-pulling two years of orders every time.
3. Collapse multiple titles into one SKU so fitment-specific listings still forecast as one stocked part.
4. Measure demand pattern and seasonality across the available history window.
5. Compare demand against owned stock, incoming POs, and vendor-backed coverage.
6. Rank recommendations by urgency, margin, lead time, and budget impact.

History Window

You can save the forecasting history window per shop.

• 3 months — recent trend heavy
• 6 months — balanced recent planning
• 12 months — stable baseline
• 24 months — best for seasonal products and year-over-year comparison

Tip

Use 24 months when seasonality matters. Use a shorter window when recent trend changes matter more than last year’s behavior.

Coverage Planning

Forecast recommendations are driven by two business controls:

• Target days on hand — how much inventory you want to hold
• Supplier lead time — how long replenishment takes to arrive

If a supplier lead time is longer than your target days on hand, Stockr raises the effective coverage target so you are not planning to stock out before replenishment arrives.

Recommendation Output

Each SKU recommendation can include:

• Forecast / month — expected monthly demand
• Owned cover — current stock plus incoming PO coverage
• Vendor cover — supplier-backed inventory that may avoid stocking locally
• Suggested reorder point — forecast-derived threshold
• Budget plan — how much of the available stocking budget should be allocated to the SKU
• Action — buy now, source from vendor, or set up supplier

Manual vs Forecast Reorder Policy

Stockr supports two replenishment modes per SKU:

• Manual — use the saved reorder point directly
• Forecast — use the forecast engine’s suggested reorder point

This lets you keep hard manual thresholds on some SKUs while using forecast-driven replenishment on others.

Budget Planning

If you provide a stocking budget, Stockr does not spread money evenly across all SKUs. It ranks opportunities so the budget is used where it should matter most first.

That ranking considers:

• stockout urgency
• demand signal
• margin contribution
• supplier lead time
• whether supplier-backed stock already covers demand

Data Sync

Forecasting data sync is designed for busy stores:

• bounded Shopify reads
• cached reusable history in D1
• incremental refresh after initial backfill
• no full-catalog forecasting pull

This keeps forecasting practical for stores that sell a lot of orders but do not want unnecessary API load.