# Recommendations on zero-result searches: +2.74% revenue

- Outcome: Won
- Page type: Other (Ecommerce)
- Elements: Filters, sorting & site search
- Test run by: [Optimizely](https://liftarchive.com/practitioners/optimizely/)
- Commentary by: LiftArchive (our analysis, not theirs)
- Original source: https://www.optimizely.com/field-notes/articles/experimentation-use-cases-retail-search-results
- Page: https://liftarchive.com/test/optimizely-retailer-zero-result-search-recs/

Sending shoppers whose searches found nothing to matched product recommendations lifted revenue by 2.74% and click-through by 2.11%. Optimizely ran this test for an online retailer and published it as an Optimizely Field Notes use case. Optimizely puts the annual gain at about $3.68M.

## Result

**+2.74% revenue**

- +2.74% revenue.
- +2.11% click-through.
- About $3.68M annualized gain. This is Optimizely's own projection.

## Control

A search with no matches showed a no-results page.

## Variant

A search with no matches sent shoppers to product recommendations chosen by a machine matching system.

## Why it likely won (our reading)

- A no-results page is a dead end, and many shoppers leave from it.
- Relevant alternatives give shoppers something to click instead of starting over.
- Shoppers who search have clear intent, so even close matches can turn into sales.

## Caveats

Vendor-reported and anonymized, with no sample size, duration or confidence level shared. The annualized figure is a vendor projection.

## How to run this test

- Hypothesis: If we show matched product recommendations when a search returns nothing, then more shoppers will keep browsing and buy because they get relevant options instead of a dead end.
- Primary metric: Revenue per searching visitor
- Guardrail: Click-through from search
- Guardrail: Exit rate from search
- Guardrail: Return rate
- Who should test it: Stores with large catalogs and many searches, where zero-result queries are common. If few searches come back empty, fix your synonyms first and the gain will be small.

---

Credit: Optimizely ran this test and owns the result. Summary and commentary by LiftArchive (https://liftarchive.com/test/optimizely-retailer-zero-result-search-recs/).
Usage: Free to use, quote and build on, with credit and a link: name the practitioner or organization that ran the test and link to its LiftArchive page. The results belong to the practitioners who ran and shared them; the summaries and commentary are LiftArchive's.