# Separating real use cases from vendor hype
A vendor demos a "virtual try-on" that drapes a dress onto a model in real time. The room nods. Then someone asks: "Will this work on our 40,000 SKUs, or just the 12 you hand-picked for the demo?" Silence. That question, not the demo, is where the real evaluation begins.
This lesson gives you the questions to ask before you sign. The goal is not cynicism. It is fluency: knowing which AI pitches survive contact with your actual data, catalog, and problem.
Machine learning (ML): software that learns patterns from data instead of following hand-written rules.
A surprising share of "AI" fashion features do not need ML. Before evaluating a model, test whether a simpler tool solves the same problem.
Examples of problems that usually do NOT need ML:
Problems that genuinely benefit from ML:
The rule: if a problem can be solved with a rule you could write on a whiteboard, ML is overkill. It adds cost, latency, and failure modes for no gain.
Demos use a curated subset. Your catalog is the real test.
Ask the vendor: "Show me this running on 500 random SKUs I choose, including our worst product photos." A virtual try-on trained on clean studio images often breaks on:
SKU (Stock Keeping Unit): a unique code for each product variant, for example one dress in size M, blue.
A mid-size apparel retailer can carry tens of thousands of active SKUs, refreshed seasonally. If a try-on tool needs manual 3D preparation per garment, the labor cost scales linearly and kills the ROIROIReturn on Investment: the ratio of net profit to the cost of an investment. A 300% ROI means each dollar invested returns $3.Voir la définition complète →. Ask directly: cost per SKU to onboard, and how much is automated.
Data readiness (whether your data is clean, labeled, and accessible enough to train or run a model).
Most AI projects in fashion stall here, not on the algorithm. Run this checklist against your own systems before any pilot:
| Data asset | Ready? Ask yourself |
|---|---|
| Product images | Consistent angles and backgrounds? Or a mix from 50 suppliers? |
| Attribute tags | Is "color" filled for every SKU? Standardized values? |
| Return reasons | Do you capture "too small" vs "didn't like fabric"? |
| Purchase history | Linked to a stable customer ID across web and store? |
If half these cells are "no," a personalization or fit model has little to learn from. The vendor's demo works because their sample data was pristine. Yours may not be.
A quick way to check attribute completeness before a meeting:
# % of SKUs missing a color tag
missing = df['color'].isna().sum()
total = len(df)
print(f"{missing/total:.1%} of {total} SKUs missing color")
# Output example: 34.2% of 41,880 SKUs missing colorIf a third of your catalog has no color tag, an "AI stylist" that reasons about color coordination is starting blind.
Vendors quote upside ("try-on lifts conversion 30 percent"). Interrogate the baseline and the cost side.
Return rates in online apparel are high; commonly cited industry estimates put fashion e-commerce returns in the range of roughly 20 to 30 percent (estimate, varies by market and category, and higher for Europe in some segmentssegmentsDividing a market into distinct groups of customers who share similar needs, characteristics or behaviours, so each group can be served with a tailored approach.Voir la définition complète →). Reducing returns is often a bigger prize than lifting conversion, because returns carry shipping, handling, and restocking cost.
Worked example (illustrative, plug in your own numbers):
Now the cost side:
Year-one net: 150,000 saved minus 220,000 cost = negative 70,000 USD. It only pays off if the return reduction holds and onboarding is automated. This is why the "cost per SKU" question decides the deal.
Always demand the claim be stated as incremental lift over your current baseline, measured by a proper test, not a vendor's other client.
Insist on a controlled test: randomly split traffic, show the AI feature to one group (treatment) and not the other (control), then compare. This is an A/B testA/B testA/B testing is a controlled experiment that compares two versions of something (A and B) by splitting traffic randomly to learn which performs better on a chosen metric.Voir la définition complète →.
Red flags in a vendor's evidence:
A good vendor welcomes a holdout test and helps you design it. A hype-driven one resists measurement.
For a grounding in how these systems are actually evaluated, Google's People + AI Guidebook is free and non-technical.
Vérification des acquis
1. According to the lesson, what is the core principle for deciding whether a problem needs machine learning?
2. Why does the lesson emphasize testing a vendor's tool on 500 random SKUs including your worst product photos, rather than accepting the demo?
3. 'Show me what's trending this week' is cited as a task that usually does NOT need ML. What concept does this illustrate?
4. Select ALL correct answers: Which problems genuinely benefit from machine learning according to the lesson?
Sélectionnez toutes les réponses correctes.
5. Select ALL correct answers: What is the intended mindset when evaluating vendor AI pitches, per the lesson?
Sélectionnez toutes les réponses correctes.
AI features fail in public. Plan for it before buying.
Regulatory note for 2026: in the European Union, the EU AI Act (the EU's risk-based AI law, phasing in through 2025 to 2027) sets transparency duties. Systems that generate or manipulate images (a try-on that alters a user's photo) may trigger disclosure obligations, meaning you tell users the image is AI-generated. In the US there is no single federal AI law; the FTC (Federal Trade Commission) has warned it will act against deceptive AI marketing claims. Practical takeaway: a vendor claiming "no compliance concerns" without naming these is not paying attention.
Ask these in order. The pauses tell you as much as the answers.
1. "Could a rule or filter do this instead of ML?"
2. "Run it live on 500 SKUs I pick, including flat-lays."
3. "What is your fully automated cost per SKU to onboard?"
4. "State your lift as incremental over baseline, measured by A/B testA/B testA/B testing is a controlled experiment that compares two versions of something (A and B) by splitting traffic randomly to learn which performs better on a chosen metric.Voir la définition complète →."
5. "How did you test across body types, and what triggers under the EU AI Act?"
If a vendor handles all five with specifics, you likely have a real use case. If they redirect to the polished demo, you have hype.