Copy and paste into your AI tool
You are a senior Amazon product operations specialist. You know that
return rates above 5-8% on most categories are a margin and ranking
problem — Amazon tracks return rates and uses them as a quality signal,
and high-return products face listing suppression risk. Your job is to
diagnose why a specific product's return rate is elevated and build a
plan to fix it.

I'm going to give you return reason data and review excerpts for a
product with a high return rate. Produce a structured diagnosis and
remediation plan.

STEP 1: CALCULATE THE COST OF RETURNS

Using the data I provide, calculate:
- Total returns in the period
- Return rate = (units returned ÷ units sold) × 100
- Estimated lost revenue = units returned × average selling price
- Estimated return processing cost = units returned × per-unit return
  processing cost (use $4.00 as a default if not provided; flag
  assumption)
- Total financial impact = lost revenue + processing costs + any
  restocking/refurbishment costs provided

STEP 2: CLASSIFY EACH RETURN REASON

Assign every return reason to one of four root cause categories:

LISTING PROBLEM: Customer received what was shipped but it didn't
match what the listing implied. Fix is in copy, images, or dimensions.
(Signals: "not as described," "wrong size," "color different than
pictured," "smaller than expected")

PRODUCT QUALITY PROBLEM: Item arrived damaged, failed prematurely, or
underperformed. Fix is in supplier QC, specs, or packaging.
(Signals: "defective," "broken on arrival," "stopped working," "poor
quality")

CUSTOMER ERROR: Buyer ordered wrong item, changed mind, found it
elsewhere. Largely unavoidable.
(Signals: "accidental order," "no longer needed," "bought by mistake")

FULFILLMENT PROBLEM: Wrong item shipped, damaged in transit, late
delivery. Fix is in prep/packaging or FBA quality controls.
(Signals: "wrong item," "arrived damaged," "too late")

STEP 3: PRIORITIZE ROOT CAUSES

Rank the four categories by: (% share of returns) × (fixability
weight). Use fixability weights: Listing = 1.0, Fulfillment = 0.8,
Product Quality = 0.7, Customer Error = 0.1.

STEP 4: REMEDIATION PLAN

For the top 2 root cause categories by priority score, build a
remediation plan with:
- 30-Day Actions: Quick fixes (listing updates, image changes,
  copy edits) — no supplier or production changes required
- 60-Day Actions: Mid-effort fixes (packaging upgrades, fulfillment
  prep changes, QC checklist additions)
- 90-Day Actions: Longer-lead fixes (supplier quality audit,
  product spec change, new photography)

Each action must be specific — name the exact change, not a
general directive.

STEP 5: PROJECTED IMPACT

After remediation, estimate the reduction in return rate (percentage
points) and monthly revenue recovered. Use conservative assumptions
and state them.

Output format: Use headers for each step. Use a table for the return
reason classification. Use a three-column table (Timeframe / Action /
Expected Impact) for the remediation plan.

POLICY REMINDER: Amazon tracks return rates by ASIN and may flag
listings with persistently high return rates. While Amazon hasn't
published a single universal threshold that triggers action, return
rates significantly above category averages can result in listing
suppression or account review. Verify current policy in Seller
Central > Account Health before relying on any specific threshold.

BEFORE YOU EXECUTE:

1. If I haven't provided average selling price or total units sold,
   ask before calculating return rate and financial impact.

2. If return reasons are ambiguous — e.g., "item not as expected"
   could be either a listing problem or a product quality problem —
   ask me to clarify or look for corroborating signals in reviews
   before assigning a category.

3. Do not classify Customer Error returns as fixable. If a return
   reason is clearly buyer error, say so and exclude it from the
   priority fix list.

4. If the total return count is fewer than 20 units, flag that the
   sample is small and conclusions may not be reliable.

5. After completing the plan, list any return reason that was
   difficult to classify under a "Caveats" section, and note any
   assumption you made.

=====

PASTE YOUR RETURN DATA BELOW. Include: product name and ASIN, total
units sold in the period, each Amazon return reason (exact text) and
unit count for each, average selling price, and any relevant review
excerpts that mention the product failing or not matching expectations.
Also note the period (e.g., last 90 days).

[YOUR DATA HERE]
What you'd paste after the divider
Product: Bamboo Cutting Board Set (3-piece) — ASIN B09XXXXXX
Period: Last 90 days
Units sold: 830
Average selling price: $34.99

Return reasons (from Seller Central Customer Returns report):
"Not as described" — 41 returns
"Defective/doesn't work" — 28 returns
"Poor quality/not durable" — 24 returns
"Wrong item sent" — 9 returns
"Accidental order" — 7 returns
"No longer needed" — 5 returns

Per-unit return processing cost: $4.50

Review excerpts (1-3 star):
"The large board is way smaller than it looks in the photos — I
expected something big enough for a whole chicken."

"Cracked along the grain after my second wash. Clearly low-grade
bamboo."

"Arrived with one board already warped. Packaging had no protection
between the boards."
01

Pull your return reason data from Seller Central: Reports > Fulfillment > Customer Returns. Filter by ASIN and use at least 90 days of data. Fewer than 20 total returns gives you too small a sample to draw reliable conclusions.

02

Cross-reference your return reasons with your 1-3 star reviews. Amazon's return reason categories are broad; reviews tell you the specific failure mode. "Poor quality" returns plus reviews mentioning "cracked after two uses" point to a supplier issue that "poor quality" alone doesn't resolve.

03

Fixing listing problems (bullet copy, images, dimension callouts) is almost always your fastest, cheapest lever. Resolve any Listing Problem root causes first — changes can go live in 24-48 hours and take effect in the next return cycle.

What does the Returns Rate Analyzer prompt do?
Diagnose why a specific product has an elevated return rate by combining Amazon return reason data with review signals. Classifies the root cause, estimates the revenue and fee impact, and builds a concrete remediation plan with a 30/60/90-day timeline.
What data do I need to use this prompt?
An example of the exact input format is provided on this page under "Example Input." Generally you'll prepare your data in the structure shown, paste it after the prompt body, and the AI will return the analysis described above. If you're missing any inputs, the prompt will ask you what it needs.
How long does this take to set up?
Setup time for this prompt is 30-60 mins. That includes pulling your data, formatting it to match the example, and running the prompt. Once your data pipeline is set up the first time, subsequent runs take only a few minutes.
Which AI tool should I use this with?
This prompt is designed to work with any major large language model — ChatGPT (GPT-4 or newer), Claude (Sonnet 4 or newer), or Gemini. For structured analysis, math, and tabular outputs, Claude and GPT-4 class models produce the most reliable results.
Does this prompt work for Shopify or other platforms?
This prompt is built for Amazon sellers and references Amazon-specific data points such as referral fees, FBA fulfillment fees, and ASIN-level metrics. The underlying methodology can be adapted to other platforms by substituting equivalent inputs, but the prompt as written is Amazon-first.
What skill level is required to use this prompt?
This prompt is rated intermediate. Some familiarity with your platform's data exports and basic AI prompting is helpful for getting the most out of it. Most ecommerce operators can use it productively within a single session.
Is this prompt free to use?
Yes. Every prompt in the SMB Advantage Prompt Library is free for any small business operator to use. The only cost is whatever you pay for your AI tool subscription (ChatGPT Plus, Claude Pro, etc.).
Stay in the loop

Want notes when new prompts ship?

A few times a week, field notes on what's actually working when AI meets ecommerce ops. Plus first look at new prompts and tools as they go live.