Recommendations via Experiments

📘

Overview

In this article, you will find out how to deploy product recommendations via experiments using a predefined block. Moreover, this guide will show you how to A/B test to achieve the best results.

Deploying product recommendations on your website can be challenging, often necessitating help from the IT department. However, recommendations via experiments using a predefined ready-to-use ‘Product Recommendations [web]’ block present a simple solution to effortlessly deploy personalized recommendations without coding, thus bringing value to your company fast.

Create Recommendations via Experiments

Go to Campaigns > Experiments, click on ‘+ Create new’ and insert your target website.

19991999

🚧

Warning

Please bear in mind that the target website must be integrated with the current project before creating and publishing the experiment.

In the Design tab, click on ‘Edit’, which will open your target website.

19991999

Depending on where you would like the product recommendations to be, click on the screen and then click ‘Insert’ > ‘Block’.

19991999

Scroll down to the section ‘Predefined templates’ and click on the ready-to-use predefined block ‘Product Recommendations [web]’ available for every project.

19991999

A panel will be displayed where you can modify and personalize the block with product recommendations. You will need to select a recommendation engine available for the project under the ‘Recommendation ID’ section. Furthermore, specify the currency, such as EUR.

🚧

Remember

It is important to note that the blocks only work with recommendation engines that do not initially need ‘item_id’. However, if you need to use this engine with ‘item_id’, it can be added to the Product Recommendations [web] block in the Asset manager.

730730

You can adjust various parameters, such as fonts, colors, layouts for mobile devices and desktops, and more, to achieve the perfect personalization. For example, a block adjusted to showcase four items with red background would look like this.

19991999

If you are satisfied with the block, click on ‘Confirm’ in the bottom right corner and hit ‘Save’ on the top left side of the screen.

Although this block should work for a vast majority of websites, each one is different. Therefore, testing it before hitting your real audience is highly recommended.

You can test the blocks on yourself by going to the Settings tab, for example, specifying your URL. Moreover, this tab allows you to perform various modifications to accommodate your business preferences. Afterward, just click on ‘Start’, and the website will contain the product recommendations!

19991999

A/B test

In the Design tab, you can create multiple variants of the Experiment and set up AB Testing. You can also change the preview page URL, change the variant names, and even duplicate them.

You can choose the traffic distribution of your customers in the right-middle part of the page. If you select the Automatic traffic distribution (default setting), Bloomreach Engagement will determine the best performing variants of the Experiment automatically and then prefer these variants over the less performing ones. Contrary to that, Custom traffic distribution allows you to select the percentage of your customers to see each of your variants. Note that both cases allow you to create a control group, which is a group of people who will continue to see your original page for the purpose of a better evaluation.

You can also choose to duplicate your variant.

26962696

👍

Read more

To learn more about product recommendations, experiments, and blocks, please refer to our guides.


What´s next?