- Optimizely X Web Recommendations
THIS ARTICLE WILL HELP YOU:
- Create a Recommendations experiment
- Add or edit content, product, or category recommendations on your site
Optimizely X Web Recommendations makes it easy to add recommendations to any page on your site and measure the impact with Stats Engine.
This article walks you through how to add recommendations to your site.
First, you'll create an experiment that targets the pages on your site where you'll deliver recommendations: across your entire site, or only on product detail pages, for example. You can also add an audience to specify who should see those recommendations. Perhaps you only want visitors browsing on mobile devices to see your Recommendations experiment. Then, you'll configure the Recommendations algorithm and decide where it will display.
You can use Recommendations as a standalone product to deliver hands-off revenue. If your Optimizely X plan includes Recommendations but not Experimentation or Personalization, you won't be able to use the Optimizely Editor to make visual changes beyond the layout of your recommendations. Learn more about using multiple Optimzely X Web together in our article on using Optimizely Recommendations with Experimentation and Personalization.
Create an experiment
Navigate to the Experiments dashboard. To create a new Recommendations experiment, click Create new and select Experiment.
Name your Recommendations experiment.
Click () to add an existing page where you'll show recommendations. Or, click Create New Page to add a new page in Optimizely X.
Add an audience to show your recommendations to a certain group of visitors. Leave this field blank to show recommendations to everyone.
With the standalone Recommendations product, you can target visitors browsing on Desktop or Mobile. For more audiences, read about using Recommendations with Optimizely X Web Experimentation or Optimizely X Web Personalization.
Click () to add an existing audience. Or, create a new audience.
Choose metrics to measure the success of your recommendations. Click () to add an existing metric. Or, create a new metric.
Use traffic distribution to decide what percentage of visitors see your recommendations. By default, Optimizely shows 50% of visitors the variation with recommendations and 50% the original variation.
Adjust the distribution to show recommendations to a higher or lower percentage of visitors, if you like.
Click Save to create the experiment.
Next, you'll choose an algorithm and decide where to show your recommendations.
Use the Editor to choose an algorithm and place the recommendations on your page.
Navigate to the Manage Experiment dashboard and select a variation.
Then, click Create to make changes to the variation.
Find and select the Recommended Products extension.
Modify the recommendations so they look the way you'd like.
Click the Header Text to modify the header for your recommendations. For example: "You might also like."
Click Maximum Products to select the number of recommendations to show at one time.
Next, click the Algorithm dropdown to choose an algorithm for your recommendations.
Optimizely currently offers five algorithms.
Co-browse: "Website visitors who viewed this product also viewed these other products."
Co-buy: "Website visitors who bought this product also bought these other products."
Popular: "Items that website visitors most frequently viewed or bought."
Recently viewed: "Items that you previously browsed."
User-based: "You browsed similar products as this group of website visitors, and they tended to like these products."
Decide where you'd like your recommendations to display.
To change the position of your recommendations module, click Insert After Selector and add the selector that the module will appear below.
Finally, choose the timing for loading your recommendations on the page: synchronous or asynchronous.
Consider using asynchronous changes to allow the rest of the page to load while your recommendations load. If you'd like the rest of the page to wait for the recommendations to load, choose synchronous timing.
QA your Recommendations experiment with the Preview tool. When it looks and works the way you'd like, publish your experiment.
Congratulations, your recommendations are live to the world! To measure the impact on your key metrics, check out the Results page.