Sales forecasting and purchasing for auto-parts businesses.

Tens of thousands of references, parts that sell two or three times a year and suppliers who import with long lead times. Have the part when the workshop asks for it, without piling up the ones nobody looks for.

A day in this trade

Long lead times, costly mistakes
With a supplier who takes weeks, ordering late means weeks without the part. The real lead time matters more here than in a fast-replenishment trade.
The reference that sells twice a year
The daily average of a sporadic part misleads: it is almost always zero and then suddenly not. It needs a model built for that.
Parts for models no longer on the road
What was bought for a vehicle model that stopped selling sits in the warehouse for years.

Which part of StockAI applies

Learned import lead time
You start with the lead time the supplier declares; with each reception you log, StockAI learns the real one and uses it from the third delivery.
Intermittent sales, their own model
References with many periods without a sale compete with Croston and ETS, and the global model learns from how the rest of your catalogue behaves.
ABC-XYZ for the cushion
Safety stock goes to the parts that weigh most and are hardest to predict, instead of being spread equally.
Several warehouses and transfers
With more than one warehouse, StockAI suggests moving before buying, and only if the lending warehouse keeps at least 30 days of cover.
Lowest-total-cost order
The order optimiser includes fixed freight and minimum orders to propose the lowest-total-cost combination.
Sample data

A sample morning

Four references of an imaginary parts house, as StockAI orders them.

Sample data
Product
Sales per day
On hand
Supplier lead time
Reorder point
Cover
Signal
Oil filter (common model)16406 days9 days2.5 daysORDER NOW
Front brake pads86010 days14 days7.5 daysORDER SOON
Timing belt39014 days19 days30.0 daysOK
Ball joint (discontinued model)0.24021 days28 days200 daysOVERSTOCK

Sample data, invented to illustrate the rule: not from a customer and not a measured result. Cover is on-hand ÷ sales per day; the reorder point is the lead time plus the safety cushion, in days.

How to read the example

The filter covers 2.5 days with a supplier who takes 6: PEDIR YA. The pads, with 7.5 days of cover and a 10-day lead time, are already under the 14-day reorder point. The ball joint has 200 days of stock for a part that barely moves: SOBRESTOCK.

Try without signing upSee the full rule

Worth knowing

  • StockAI does not ship a cross-reference or vehicle-fitment catalogue: it works with your codes.
  • A reference with fewer than 20 periods of history is left out of the forecast and shows as SIN DATOS.
  • The forecast range is not a guarantee: it tells you how far to trust the suggested quantity.
Try without signing upCreate an account

Keep reading

Put your own AI to work forecasting your sales. Today.

Three ways to start, depending on how much you want to commit right now. All three lead to the same product.

Create your account

With the whole engine. Upload your sales file and see your first forecast, and with it your first list of what to order.

Create my account

Look before giving your email

An instant trial account with sample data. It lasts 24 hours and is then erased.

Try it without signing up

Talk to us

For the corporate plan, the source code, or to see it with your data and someone beside you. We answer within 24 hours.

Message us on WhatsAppEmail us

Sales and contact: contacto@stockai.es. Phone: +506 7186 2820.

Sales forecasting made in Costa Rica, for companies across Latin America.