Skip to main content
Nova Analytics
Try for free

How to analyze Amazon Search Query Performance data with AI

To analyze Amazon Search Query Performance with AI, the assistant needs live access to every week of your Brand Analytics data, your ads and your listings, and Nova's MCP connector gives Claude, ChatGPT and other assistants that access. Through Nova, the assistant finds the queries where you lose share, says whether impressions, clicks, conversion or price is the weak step, and checks whether your ads cover them.

Updated

Connect your AI Copy the playbook
Example with made-up figures
Claude

Where am I losing share on Amazon search?

NUsed Nova

Your biggest gap is "bamboo cutting board": 42,000 searches in the week and you hold 1.2% of impressions, though you convert above the market. "Cutting board set" has half the market's click rate, so test the main image. "Large wood cutting board" converts at 3.2% against 7.4%, with your price at $48 against $32.

Ask anything

The playbook

Every step calls a Nova tool that reads your live Amazon data, so paste this into Claude, ChatGPT or any assistant connected to Nova's MCP server. Change the grain if you want a monthly read.

This needs an assistant connected to Nova. Start the 14-day free trial, then connect your assistant.

Use Nova to analyze my Amazon Search Query Performance and tell me what to fix.

Period: the latest complete week. If I ask for a trend or a year-over-year read, use grain "month".

1. Get the period. Call Nova's query_sqp with grain "week", no dates, and read period.covers. Those are the dates for every other call. They run Sunday to Saturday. If dataFloor is present, say the plan withheld older data.

2. Read the market you are really in. Call Nova's query_sqp with groupBy "keyword", queryTypes ["core", "presence", "suggested"], and the metrics search_volume, search_volume_wow_pct, your_impression_share, your_click_rate, market_click_rate, your_conversion_rate, market_conversion_rate, your_median_purchase_price, market_median_purchase_price and your_purchases, sorted by search_volume, limit 30. Leave out too_broad and long_tail, because they are category noise. Use summary for any total: never add market figures across rows.

3. Name the weak step, per query. Impression share low: you are not being seen. Click rate below the market: main image, title or price. Conversion rate below the market: price, reviews or listing. Your median price above the market's: say so. Read attrs.reason and attrs.action for Nova's verdict, and say when you disagree with it.

4. Check your brand. Call Nova's query_sqp with queryTypes ["own_brand"], groupBy "keyword", sorted by search_volume, limit 10. Then the same with ["competitor"]. Say where rivals take purchases on your brand terms, and where you take theirs.

5. Check your ads. For the top 10 queries from step 2, take every spelling in attrs.variants. Call Nova's query_search_terms with searchTerms set to those spellings, and from and to set to period.covers, with spend, sales, clicks, orders and acos, groupBy "searchTerm". Say which big queries get no ad spend and which spend without selling.

6. Check the listing. For the products behind the weak queries, call Nova's query_sqp with groupBy "parentAsin" to name them, then query_listing_health for their title, bullets and backend keywords. Say whether the query's words appear in the listing.

7. Check the trend. For the top 5 queries, call Nova's query_sqp with grain "month", groupBy "period" and keywords set to one query at a time, with search_volume and your_impression_share, over the last 6 months. Say whether the gap is new.

8. Report, one row per query, largest first: search volume, your share, the weak step, the figures behind it, ad spend on it, and one action. Then the three actions worth the most.

Rules: this is every seller's organic behaviour on the query, not your ads. Say which period the data covers. Never add market figures across rows. Say which figures are missing and why, and relay every notice Nova returns. You cannot change anything on my account.

Raw markdown

How Nova customers use this

Real requests from Nova customers, names removed.

  • “Keyword targets for one ASIN, to know which Search Query Performance queries have a live keyword target and what ACOS they run at.”

    What the assistant did

    It crossed the latest complete week of Search Query Performance with the keyword targets.

    Nova tools used (2)
    1. query_sqp
    2. query_advertising

  • “Analyze the latest complete SQP period for listing growth opportunities.”

    What the assistant did

    It crossed the period with sales, sessions, conversion, price and ads for the exact SQP week, then audited the listing content for gaps.

    Nova tools used (4)
    1. query_sqp
    2. query_metrics
    3. query_advertising
    4. query_listing_health

  • “Market-wide or our side? Weekly market searches and purchases against our share, after a sales drop.”

    What the assistant did

    It read the daily funnel, then the market against our share, then ruled reviews, listings and stock in or out.

    Nova tools used (5)
    1. query_metrics
    2. query_sqp
    3. query_reviews
    4. query_listing_health
    5. query_inventory

  • “Which parent ASINs capture the purchases on one query, and which campaigns convert it.”

    What the assistant did

    It crossed keyword targets and search terms with the query's purchases by parent ASIN.

    Nova tools used (4)
    1. list_accounts
    2. query_advertising
    3. query_search_terms
    4. query_sqp

  • “Market purchase trend on core search queries, to refine a shipment size for the holidays.”

    What the assistant did

    It read current stock, the weekly sales trend and last year's seasonality, then the market's trend on the core queries.

    Nova tools used (3)
    1. query_inventory
    2. query_metrics
    3. query_sqp

What does Search Query Performance tell you that ads data does not?

It shows what shoppers type on Amazon: searches, impressions, clicks, cart adds and purchases on a query, for the whole market and for your products. That is organic behaviour across every seller. query_search_terms is different: it only shows what people typed before clicking your ad.

Which queries should I actually look at?

Not all of them. Nova classifies each query against your product. core, presence and suggested are where you can act. too_broad and long_tail are category demand, and left in they dominate any total, so the playbook filters them out. Each row carries Nova's reason and suggested action, and variants lists the spellings merged into that query.

Is it impressions, clicks, conversion or price?

Compare your rate with the market's on the same query. your_click_rate below market_click_rate points to image, title or price. your_conversion_rate below market_conversion_rate points to price, reviews or listing. your_median_purchase_price against market_median_purchase_price shows how you are priced.

Volume up, your share flat or down

Where it points

Demand you are not catching

What to do

Bid on it, and check the query's words are in the listing

Share fine, click rate below the market

Where it points

Shoppers see you and pass

What to do

Main image, title, price

Clicks fine, conversion below the market

Where it points

They come and do not buy

What to do

Price, reviews, listing content

Your median price above the market's

Where it points

Possibly priced out

What to do

Check it against your margin first

Big query, no ad spend

Where it points

A gap in your ads

What to do

Test a keyword target

Rivals buying on your brand terms

Where it points

Brand defence

What to do

Bid on your own brand terms

Volume down, share flat

Where it points

Demand, not you

What to do

Wait, and check the monthly trend

Do my ads cover these queries?

Group by keyword and each row carries variants. The assistant passes every spelling to query_search_terms, because matching one string misses campaigns. It uses period.covers as the dates, because SQP weeks run Sunday to Saturday and other weekly series do not.

Example with made-up figures

A week of Search Query Performance, worked through

bamboo cutting board

Search volume

42,000

Your share

1.2%

Your click rate against the market

1.9% against 1.8%

Your conversion against the market

9.0% against 8.5%

Ad spend

$310

Action

Share is the gap: raise the bid

cutting board set

Search volume

18,500

Your share

3.4%

Your click rate against the market

0.9% against 1.7%

Your conversion against the market

8.1% against 7.9%

Ad spend

$120

Action

Half the market's click rate: test the main image

large wood cutting board

Search volume

9,200

Your share

5.1%

Your click rate against the market

2.1% against 1.9%

Your conversion against the market

3.2% against 7.4%

Ad spend

$95

Action

Price is $48 against $32: check the margin first

charcuterie board

Search volume

31,000

Your share

0.2%

Your click rate against the market

none

Your conversion against the market

none

Ad spend

$0

Action

No ad spend: test a keyword target if the product fits

Can I just upload my SQP report to ChatGPT?

You can, one report at a time. A CSV holds one period, for one ASIN or brand, with no ads, no listing content and no history unless you combine them yourself. With Nova the assistant reads every period, your ads and your listings, and each query is already classified.

What this cannot tell you

  • Search Query Performance needs Brand Analytics, so it needs Brand Registry on Seller Central. Amazon does not serve it to vendors.
  • Weekly data runs about 10 days behind, and monthly about 7 weeks.
  • SQP weeks run Sunday to Saturday, so pass period.covers to any other tool.
  • A query's figures repeat on every parent ASIN that ranks on it, so totals come from summary.
  • Data is per parent ASIN, not per SKU.
  • It shows the market on a query, not each rival's share.
  • A trial may withhold older periods: the answer says so in dataFloor.

To see this in the app, see the SQP keyword optimizer. For ads that spend without selling, see wasted PPC spend.

Questions sellers ask

How do I analyze Amazon Search Query Performance data with AI?

Connect your account to an assistant through Nova, then paste the playbook. It reads the latest complete week, keeps the queries you can act on, compares your funnel with the market's on each, and checks your ads and listing.

Do I need Brand Registry?

Yes. Search Query Performance comes from Brand Analytics. Amazon does not serve it to vendors.

How recent is the data?

Weekly data runs about 10 days behind, and monthly about 7 weeks. The answer gives the exact dates it covers in period.covers.

Can it compare my price with the market?

Yes, as the median purchase price on each query, yours against the market's.

Can it see my competitors' sales?

No. It shows the market on each query and your share of it, and competitor queries show purchases on rival brand terms. It does not show each rival's sales.

Does this change anything on my account?

No. Every tool in this playbook only reads. The connection uses OAuth, per account, and you can revoke it at any time.

Ask your assistant where you are losing share

Connect your AI