Book an intro callIntro call
Your forecast decides your inventory. And it's running on averages.
Too much stock of one item, sold out on the next. Enter your revenue, inventory and margin and see what a better forecast earns you per year.
A solution architect at the table.
At Stratalytic the solution architect at the table also builds the forecasts, no sales team. In 30 minutes we look at the assortment and the current method, with an honest verdict on whether a comparison on the data is worth doing. If the current forecast is already fine, that is the answer.
- 2 out of 3Order emails at a wholesaler nobody retypes anymore
- 40% to 86%Forecast accuracy at one client
- WeeksComparison turnaround
- 20-40%Less forecast error vs rule of thumb
Sound familiar?
Purchasing runs on last year's average, and it shows
Too much capital in slow-moving stock, empty shelves on risers. The forecast error is invisible on a dashboard but very visible in working capital and lost sales.
The planning is in one head, and the quote for a suite hurt
One experienced person knows what to order, until they are away. Enterprise planning software bills per SKU per month, forever, and promotions and web platforms still don't fit the standard model.
Every supplier order is a gut-feeling decision
Long lead times and minimum order quantities make every purchase order expensive to get wrong, in both directions.
How it works, measured instead of promised
- 01
30 minutes with the solution architect
The call is with the solution architect who builds the forecasts, no layer in between. Together we look at the assortment, channels and current method, with an honest answer on whether a better forecast is realistic for this data.
- 02
Forecast comparison on your own history
Under NDA we run our forecasts against the current method and a simple rule of thumb, on the real sales data. The improvement per product group is on paper, measured, not promised.
- 03
From forecast to purchasing decision, in the existing systems
The forecast plus the translation into reorder points and purchasing advice, integrated with what is already used. Fixed price, and the buyers see the advice in the systems they already work in.
Why not a planning suite or a spreadsheet?
| Excel | Planning suite | Stratalytic | |
|---|---|---|---|
| Handles the deviations (promotions, channels, season) | Average-based formulas | Standard model, fixed settings | Built on the company's own data |
| Proof before committing | None | Vendor demo | Comparison on the company's own history |
| Cost model | Free, but error is expensive | Subscription per SKU, forever | One-off, fixed price |
| What the buyers get | A number per product | Advice from a standard model | Reorder points and purchasing advice |
Before the call
Why not Slimstock, Optiply or another planning suite?
Those packages are strong for companies that fit their standard profile. If reality deviates (promotions, sales through web platforms next to own channels, import lead times, hard seasonality), a standard model calculates with averages. A custom forecast is built on the company's own data and deviations, paid once instead of a per-SKU subscription.
How do I know it will actually be better?
We measure it before anything is decided. In a comparison we put our forecast next to the current method and a simple rule of thumb, on the company's own sales history, on paper per product group. If we don't demonstrably beat the current approach, it stops there, there is no proposal, and the company keeps a free insight.
We already built something ourselves and it works. What do you add?
Good sign. Then the question is no longer whether it can be done, but whether you are getting everything out of it. That is where most of it stalls: Gartner expects 30% of AI projects to be dropped after the trial, and MIT found that 95% of trial projects deliver no result that shows up in the numbers. Rarely because the forecast does not work, usually because nobody owns the number. On top of that, what is possible shifts quickly, and keeping up with that does not fit alongside running an operation. We calculate up front on the company's own data what there is to gain, free, and then make sure it actually runs. On a forecast running on averages, accuracy went from 40% to 86%.
How long does it take and what does it deliver?
The comparison is fixed-scope and gives a result within a few weeks. The full project (forecast + integration with the inventory and purchasing process) is one-off instead of per SKU per month. The effect shows in stock: 10-15% less overstock and 20-40% less forecast error than the rule of thumb. Check it with the calculator on this page. The call itself takes 30 minutes, no obligation.
What data is needed?
Sales history per item per week (at least ~2 years for seasonality), ideally plus the promo schedule and stock levels. That almost always already sits in the webshop, POS, ERP or fulfilment system, extracting it is part of the work. Messy data is normal: the comparison shows what is usable, and we say so honestly if the answer is 'not yet'.
What if it does not work, and do we need a new system?
Then we find out early and for free, before anything is invoiced, and there is no proposal. No new system is needed: the advice shows up in the ERP or purchasing tool that is already there, and the team decides.
What happens with the forecast in practice?
A prediction nobody uses is worthless. We translate it into the decision: reorder points, purchasing advice per supplier, promo weeks planned separately. The buyer gets a list, not a chart: order this, skip that, and why.