Research library
Product search and shopper answers research
Source data and original analysis for ecommerce teams. Start with the featured study, inspect the definitions and calculations, and follow each finding to its source.
13research pages
260source citations
18research exhibits
November 2026library updated
Featured study
Product Compatibility Search Statistics for Ecommerce
Analyze ecommerce compatibility searches by device family, candidate count, query length and match label in Amazon’s public benchmark and Baymard’s UX research.
139 citations · 6 charts · Updated November 2026 Read the study- 33 of 47 held-out named-device queries had exact and non-exact candidates.
- 44.7% of the same named-device queries included a substitute.
- 76.3% of other U.S. held-out queries had mixed exact and other labels.
- 10.0% of judged pairs in that other-query group were irrelevant.
Research library
Explore the studies and their source data.
- Non-product ecommerce search statistics for shopper help questionsWhen should search return policy and help answers alongside catalog results? Published research, original calculations and limits for DTC merchants.6 citations · 1 charts66% of benchmarked sites had non-product search issues.
- Ecommerce autocomplete statistics for editable search suggestionsShould a shopper be able to edit an autocomplete suggestion before submitting it? Published research, original calculations and limits for DTC merchants.7 citations · 1 charts58% of benchmarked sites failed editable suggestion behavior.
- Conversation timing statistics for warmth and problem solvingField conversations and controlled experiments examine when warm and practical language helps customers, with satisfaction kept separate from sales.22 citations · 1 chartsNaturalistic retail transcripts gained 0.49 satisfaction points.
- Semantic search statistics from a randomized retail experimentA 1.85-million-consumer experiment connects semantic query rewriting with purchases, while separating search engagement from product-page conversion.36 citations · 1 chartsSemantic query refinement added 1.01 purchasers per 1,000.
- Ecommerce model number search statistics across exact and substitute productsAn Amazon ESCI reanalysis tests how often exact products, substitutes and complements repeat the model-like token in a product search.4 citations · 1 charts
- Long-tail ecommerce search statistics for exact matches and substitutesA query-length study of 22,458 Amazon ESCI test searches shows where exact products and alternatives appear in candidate lists.4 citations · 1 charts
- Multipack product statistics for quantity matches and substitutionsA public search benchmark shows when product titles disagree with the pack size shoppers asked for.4 citations · 1 charts
- AI shopping recommendation accuracy statisticsAgenticShop measures how well shopping agents meet buyer requirements. See what its results mean for compatibility, price and other checkout replies.11 citations · 1 charts
- Ecommerce product review statistics and what shoppers use to decideCompare observed review and conversion patterns with shopper survey data, and learn which product reviews can actually answer a checkout question.9 citations · 1 charts
- AI shopping price and availability error statisticsSeparate wrong prices, stock problems and nonexistent products in eight AI shopping platforms, and use the breakdown to plan a checkout verification test.8 citations · 1 charts
- Product search statistics on exact matches and substitutesAn analysis of 425,762 public product judgments shows why a similar item needs a clear label when a shopper asks for a specific option.6 citations · 1 charts
- Product color data statistics for exact matches and substitutesAn original join of 25,466 judged search candidates shows how often product color fields are blank when shoppers name a color.4 citations · 1 charts
Method
Follow the evidence and its limits
- 01
Identify the population
Every study states who or what was measured, and when.
- 02
Inspect the calculation
Downloads preserve source values, denominators and derived results.
- 03
Keep the scope
Historical data and controlled comparisons retain the conditions that determine where the findings apply.
Study methods distinguish original calculations, reported experimental results and practical interpretation.