Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Markdown Optimisation for Seasonal Stock
AI & Machine Learning

Markdown Optimisation for Seasonal Stock

Cut too early and you give away margin; too late and you are left with stock. How to structure the decision with data rather than instinct.

Updated 2 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

Markdown is a timing problem as much as a depth problem. Predicting sell-through at the current price against remaining weeks tells you whether action is needed, and a staged reduction usually beats one large cut.

Two ways to lose money on the same stock

Mark down too early and you discount units that would have sold at full price. Too late and you are clearing at a deeper cut, or carrying stock into a season where it is worth less again.

Most businesses lean one way consistently, driven by whichever mistake was most painful recently. That is not a strategy, and it is visible in the data if anyone looks.

The question is sell-through against time remaining

The core calculation is straightforward: at the current rate of sale, will this stock clear before the end of its selling window? If not, by how much is it short?

  1. Estimate the remaining selling weeks for the line.
  2. Predict the sales rate at the current price, using the line's own recent performance and comparable products.
  3. Project the closing stock position.
  4. If it will not clear, estimate the uplift needed - and what discount depth has historically produced that uplift for similar products.
  5. Compare the margin cost of the discount against the expected residual value of unsold stock.

That last comparison is what makes the decision rather than a rule of thumb. If unsold stock has meaningful residual value, waiting is cheaper than it looks; if it will be written off, acting early is worth more.

Staged reductions usually beat one big cut

A single deep markdown clears stock and gives away margin on units that would have moved at a smaller reduction. Successive smaller cuts capture more of the demand curve.

ApproachMargin capturedRisk
One deep cut, lateLowestAlso the most residual stock beforehand
Staged reductionsHighest in most casesNeeds monitoring and discipline
Early small cutGood if demand respondsGives away margin if it would have sold

Staging requires the discipline to review on a schedule and act. Businesses that set a markdown calendar and stick to it generally do better than those making ad hoc decisions under pressure at the end of a season.

Sizes and variants complicate everything

Aggregate sell-through hides the real position. A line that is 70% sold may have cleared the middle sizes and be sitting on the extremes, which will not clear at any sensible discount.

Decide at the level the customer buys. Marking down a whole line because the broken size curve looks like slow sell-through discounts units that would still have sold at full price to the customers who wanted them.

Measuring whether it worked

Markdown effectiveness is hard to measure because there is no control - you cannot also not mark down. The practical approach is comparison across similar lines treated differently, and consistency in how decisions are recorded.

Record the decision, the reasoning and the state at the time, for every markdown. After a couple of seasons that gives an evidence base connecting decisions to outcomes, which is what turns this from instinct into a process.

The markdown decision is made every week you do not make it.

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

How much history is needed?

Ideally several seasons of comparable products, including the markdown decisions and their outcomes. Sales data alone without the price history is much less useful.

Does this work for non-seasonal stock?

The same logic applies to any stock with a shelf life or obsolescence risk, including technology and dated packaging.

Should discounts be the same across channels?

Not necessarily, though inconsistency is visible to customers and can create problems. Treat it as a commercial decision rather than an optimisation output.

What if we have never recorded markdown reasons?

Start now. Even a short note against each decision becomes valuable within two seasons.

Keep reading

More on AI & Machine Learning

Start here

Want machine learning project details from us?

Tell us what you are trying to predict and roughly what data you hold. We will come back with an honest view on whether machine learning is the right tool, what the work would involve and a realistic cost range. If a spreadsheet 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 →