Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Why Are We Overstocked on Some Products and Out of Stock on Others at the Same Time?
Problems We Solve

Why Are We Overstocked on Some Products and Out of Stock on Others at the Same Time?

Too much of the wrong stock and not enough of the right. We build machine learning demand forecasts per product so cash goes into stock that actually sells.

Updated 3 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

Carrying excess stock and suffering stockouts at the same time usually means reorder rules treat every product the same way. A machine learning forecast per product, with a range rather than a single number, lets you set reorder points and safety stock that reflect how each item actually sells, so cash moves from slow lines into the ones customers want.

A full warehouse and an empty shelf

The warehouse is full. There are pallets of products that have barely moved in months, cash tied up in them, and a stock take that keeps flagging the same slow lines. Yet customers are being told the product they want is out of stock, and the sales team is chasing suppliers for express deliveries on the lines that actually sell.

Both problems land on the same people. Finance wants stock reduced. Sales wants more availability. The buying team feels they cannot win, because every attempt to fix one side makes the other worse.

Why both happen together

Most stock systems reorder with simple rules: a minimum level, a fixed reorder quantity, or "order the same as last month". These rules are usually set once, often the same way across whole categories, and rarely revisited. A product that sells steadily and one that sells in bursts get the same treatment. So do a product with a reliable supplier and one with erratic lead times.

The result is predictable. Steady, slow lines accumulate because the reorder quantity is too high for them. Volatile, fast lines run out because the buffer is too small for their swings. Averages hide both problems, because on average stock looks about right.

What the imbalance costs

SideWhat it costs
Excess stockCash tied up, storage space used, markdowns and write-offs
StockoutsLost sales, customers trying a competitor, emergency orders
Express restockingHigher freight costs and supplier goodwill used up
Staff timeBuyers firefighting instead of planning
Customer trustRepeat customers learn not to rely on you for key lines

The overstock is visible on the balance sheet. The lost sales are not, which is why businesses often cut stock across the board and make the availability problem worse.

How we set stock by how each product actually sells

  1. We pull sales, stock and purchase order history from your stock system, ERP, Shopify or WooCommerce, and mark stockout periods so lost sales are not mistaken for low demand.
  2. We group products by how they sell (steady, seasonal, intermittent, new) because each pattern needs a different forecasting approach.
  3. We build demand forecasts per product with a range, for example a likely level and a high level, rather than one number.
  4. We model supplier lead times from your purchase history, including how much they vary, since an unreliable supplier needs more buffer than a reliable one.
  5. We combine the two into suggested reorder points and quantities per product, based on the availability you want for each group, so key lines get more cover and slow lines get less.
  6. We present this as a weekly reorder list or feed it back into your stock system, with overstocked lines flagged for action such as pausing reorders or promotions.

We backtest the approach on your past data before anyone relies on it, so you can see how it would have handled the periods that went wrong.

What the buying team sees

A reorder list where each suggestion reflects that product's own pattern. Slow lines stop being topped up by default. Fast, volatile lines carry enough buffer to ride out a busy week or a late delivery. Overstock is flagged early, while there is still time to act.

The conversation with finance changes too. Instead of a blanket instruction to reduce stock, there is a list of which lines are over-held and why, and which need more.

Buyers still decide. The suggestions come with the reason behind them, such as a seasonal rise or a supplier who has been running late, and any override is recorded. Over time the record shows where the model needs adjusting and where the team's knowledge adds something the data does not have.

Is this your situation?

  • You have both slow-moving excess stock and regular stockouts.
  • Reorder levels were set once and are rarely reviewed.
  • The same rule is used for very different products.
  • Supplier lead times vary and are not tracked properly.
  • Cutting stock to free cash has made availability worse.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

Can our stock system not do this already?

Some can, if they have forecasting modules set up with good data. Many businesses have the feature but use fixed rules because nobody had time to configure it properly.

What about new products with no history?

We forecast them from similar products and early sales, and flag them as lower confidence until real data builds up.

Does this handle promotions?

Yes, if promotions are recorded. They are an input to the model so a promotional spike is not treated as normal demand.

What drives the cost?

The number of products and locations, the quality of history, and whether the output needs to write back into your stock system automatically.

What do you need from us?

Sales, stock and purchase order history, your supplier list, and a view of which products matter most.

Keep reading

More on Problems We Solve

Start here

Tell us what you are guessing today

Describe the decision, the data you keep and how it is made now. We will tell you honestly whether machine learning would help, what it would need, and if a simpler fix would do the job, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →