---
title: "Run split tests"
slug: "run-split-tests"
abstract: "Overview of split testing and the importance of defining a hypothesis before creating and running a split test using Sitecore Search."
---
# Run split tests

In Sitecore Search, a split test refers to an experiment where two or more variations of a widget are tested against each other. You run different variations simultaneously to evaluate which one has the most impact as measured using key business metrics (KPIs) found in [Analytics](https://doc.sitecore.com/search/en/users/search-user-guide/monitor-performance/report-dashboards.html "Report dashboards").

Split testing eliminates the guesswork involved in optimizing search experiences and enables content managers and merchandisers to take data-driven decisions.

The following lists common examples of search use cases for split testing:

- Does my curated search result for keyword X perform better or worse than Search AI/ML-driven results?
- Does burying certain items in the search results generate conversions?
- Does boosting popular items generate more conversions?
- Does the use of an attribute *short description* to determine search relevance generate a higher click-through rate overall for keyword X?
- Does recommendation recipe A generate more conversions than recipe B on my homepage?
- Does the display of related items generate more conversions?
- What banner generates a higher click-through rate?
- What call-to-action generates the highest conversion?

## Example: Testing recipes against each other

You can create and use the following widget variations of a recommendation widget:

- Variation with a recipe to display similar items.
- Variation with a recipe to display trending items.

## Example: Testing a content strategy

You can create and use the following widget variations of a search results widget:

- Variation with a rule to pin a popular item in the first slot.
- Variation without any rules.