What we need to see
Sales history, stockouts, lead times, minimum orders and known seasonal or promotional changes.
Stock forecasting · Trade counters & industrial supply
Trade counter retail has a unique demand pattern: a small set of bestsellers covers 70% of revenue, a wide long tail covers the rest, and seasonal peaks (project season, year-end, weather-driven) hammer the bestsellers. Spreadsheets and static min/max levels can't keep up. We build forecasting tuned to your real sales velocity, across counter, trade accounts, and online.
Tell us the task, your current tools and where the work gets stuck. We will help you choose a sensible first scope.

You've got 4,000 SKUs across the trade counter, web shop, and account customers. Your buyer is working from a spreadsheet that hasn't been recalibrated in two years. Some SKUs get attention; most get reordered to the same level they always have been. Cash is tied up in slow movers; bestsellers stock out in peak weeks.
The work in context · Illustrative scenes

Use representative inputs from the business to scope stock forecasting. Agree what the system prepares and what a person needs to check.

Test normal work, missing information and failures with the team, then hand over clear review steps and practical guidance.
Trade counter EPOS sales + web shop orders + trade account orders, deduplicated and aggregated per SKU. Real sales velocity across every channel.
Per-SKU seasonal patterns (project season peaks, weather-driven, year-end), trend direction (growing, declining, stable), weekly patterns (which days are busy on counter vs. web).
Lead times per supplier, MOQs, price-break optimisation, container-fill awareness for imported lines. Recommendations respect your real cash-flow rules.
Weekly reorder list, ranked by criticality. Your buyer reviews, approves, or overrides. The system learns from overrides, which slow movers you keep in stock for one customer, which suppliers are unreliable.
We check your software version, available API or export, access permissions and any supplier fees before quoting. If a reliable connection is not available, we will explain the practical alternatives.
Sales history, stockouts, lead times, minimum orders and known seasonal or promotional changes.
Back-test the forecast against held-out trading periods and compare it with your existing reorder method.
Your buyer approves orders and cash commitments. New products and unusual demand need a separate review.
£4,800-£14,000 for build, ~£300-£700/month depending on data volume
From £4,800excluding VAT
Stock forecasting for trade counters & industrial supply
Min/max is static. Real demand isn't. AI forecasting reads the last 12-24 months of velocity, seasonal patterns, trend direction, and lead times, and recommends dynamic reorder quantities that update as data updates. Min/max says "always 30." Forecasting says "next week 47, the week after 22, here's the pattern."
Large account orders are detected and handled separately, they don't distort the everyday velocity model. If a big customer reliably orders 200 units every March, that's factored in as a known event, not noise.
Yes, recommendations can be one-click POs, or auto-generated drafts for buyer review. Multi-supplier order optimisation included (group orders to hit MOQs, batch for container fill).
Recommendations live in 6-8 weeks. Working capital and stock-out improvements typically show up over 3-6 months as old slow stock works through and new patterns take effect.
Most are. Returns, refunds, promotional bumps, one-off bulk orders. We handle the cleanup as part of build, anomaly detection, outlier removal, holiday adjustments. You don't need perfect data.
Keep exploring
A new website. More customers. Less admin.
Tell us where you want to get to. Chris or Kay will reply within one working day.