> For the complete documentation index, see [llms.txt](https://docs.intelligems.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.intelligems.io/offer-personalizations/testing-offer-personalizations.md). # Testing Merchandising Intelligems enables your org to run real-time split tests on different offers. This article will walk you through how to run a Merchandising Test with Intelligems and some best practices.\ \ Watch the Looms or follow the steps below. ## Setting Up a Merchandising Test from Test Creation Flow {% embed url="" %} If you'd rather follow written steps, read below. ## Step 1: Create a new experience Navigate to the "A/B Tests" tab in the menu on the left-hand side of the Intelligems app. Once you're there, click Merchandising. Select your type and then "Create".
## Step 2: Create your test groups Create between two and five groups to include in the test by clicking on the ‘+’ button. Name the groups for the test and use the slider at the bottom of the page to allocate what percentage of traffic will go to each group. {% hint style="info" %} The more groups you have, the longer it will take to get statistically significant results. You’ll need about 300 orders for each group in the test to detect a 10% change in conversion with 90% confidence. {% endhint %} ## Step 3: Select which Offer each group will be exposed to Once you've created your groups, go to the Modifications step. Here, you will choose what kind of Offers you're testing for each group. You can: * Leave a group untouched, as a no-offer group * Build an offer by choosing an offer type and other optional modifications * Or start by copying the contents of a Personalization that contains an Offer. See more [here](/personalizations/personalizations-getting-started.md) on how to set up a new Personalization. These details can be modified anytime during test setup and while the test is live. ## Step 4: Set up targeting if needed Targeting is an optional step. By default, a visitor will be immediately assigned to one of the test groups using its random split-test mechanism. This assignment is determined at the first visit and is stored via a first‐party cookie, ensuring that the visitor remains in the same group on subsequent visits during the offers test period. The targeting tool allows you to apply specific conditions to certain site visitors. There are a few different ways you can do this: * **Audience Targeting:** limit your users based on their device, country, UTM parameters, landing page URL, new/returning, cookies, and much more. * **Currency Targeting:** Limit your test to a single currency and/or a list of specific countries. * **Mutual Exclusion:** Prevent users from being targeted by related experiments to reduce undesired interactions under the [Mutually Exclusive Tests](/general-features/targeting/mutually-exclusive-experiments.md) option. You can learn more about targeting [here](/general-features/targeting.md). {% hint style="warning" %} **A note on targeting: If you had any targeting options set on the Offer Personalizations you used to define your test groups, these will be ignored in lieu of test-level targeting.** * Personalization-level audience targeting is ignored. The audience targeting used on the test (or lack thereof) is used in its place. * Personalization-level currency targeting is ignored. The currency targeting used on the test (or lack thereof) is used in its place. * Personalization-level page targeting is ignored. The page targeting used on the test (or lack thereof) is used in its place. {% endhint %} ## Step 5: Save your test and start it Once you have completed all the steps, you'll be able to save your test with the button in the top right. You can then start it whenever you're ready. {% hint style="success" %} Don’t worry, this won’t set the test live yet and you can come back and edit if you need to make changes! {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.intelligems.io/offer-personalizations/testing-offer-personalizations.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.