Merchandising & Buying

Size curve optimisation

Analyse historical sales by size across product categories to identify systematic over- or under-buying on individual sizes. Informs more accurate future size ratios.

Decision supportPattern-matchingCost reductionAccuracy

10–15%

reduction in size-related terminal stock

Opportunity assessment

Business Impact
3

Moderate impact. Meaningful cost or revenue improvement, likely noticeable at function level but modest relative to total business scale.

Feasibility
4

Relatively straightforward. Off-the-shelf tools handle the core task. Implementation is well-understood with good examples to follow.

Data Readiness
2

Demanding data requirements. Relies on clean, integrated data across multiple systems. Significant data preparation work typically needed.

Risk Exposure
5

Very low risk. Fully internal use. A person checks everything before it goes further. Worst case is a minor internal inconvenience.

Change Complexity
4

Light people impact. A new tool slots into an existing workflow. Minimal training needed. Most people will adapt quickly.

Tooling required

Standard LLM

Things to consider

  • SuitShop reduced its return rate by 29% after deploying Bold Metrics' AI body-data sizing (Bold Metrics).

  • Reliable size-level sales data — not just units sold but also returns by size, where available — is the critical input. Poor data produces poor curves.

  • Size curves vary significantly by category, channel, and customer demographic. A single curve across the business will mislead; you need curves by segment.

  • The output is a recommendation input for the buying team, not an automated order. Buyers apply commercial judgment on supplier minimums, cost of goods, and seasonal context.

  • The analysis is retrospective — it tells you what you should have bought, not exactly what to buy next. The value is in identifying systematic biases (consistently over-buying size XS, consistently under-buying XL) that the team then corrects with context.

  • Experiment starter: For one category with at least two seasons of size-level sales data, prompt an LLM to calculate sell-through rates and identify the three sizes most frequently over-bought and under-bought. Present to the buying team and ask whether the analysis matches their instinct. Strong agreement or useful surprises both validate the approach.

AI Transformation Playbook

Ready to assess your own opportunities?

The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.