- Optimizely X Web Recommendations
THIS ARTICLE WILL HELP YOU:
- Show visitors content or products they may be interested in, based on their browsing behaviors
- Choose the best algorithm for your recommendations
- Test and iterate on your recommendations
- Measure the impact of your Recommendations campaign
Optimizely X Web Recommendations is a recommendation engine that makes it easy to introduce visitors to products and content, based on browsing behavior. Recommendations are hands-off once they're published.
With Recommendations, you can test out different algorithms and measure the impact in real time with Stats Engine.
Recommendations also works hand-in-hand with other Optimizely X Web products for more powerful experimentation and targeting.
Optimizely X Web Recommendations is available as a standalone product. Click to learn more about Recommendations or speak to your account manager.
1. Set up Recommendations
To implement Optimizely X Web Recommendations, contact your Customer Success Manager.
Optimizely will help you complete the initial setup, so you can start creating recommendations for your site.
2. Build a Recommendations experiment
Once you've implemented Recommendations, it's easy to build and publish recommendations. You'll choose an algorithm, header text, layout, and location for your recommendations and select key metrics to measure success.
By default, Optimizely shows your recommendations to a subset of your visitors. Another subset of randomly bucketed visitors will see the original variation. Stats Engine tracks how each variation performs, so you can measure success in real time and iterate on your Recommendations experiment.
Jump in and build a standalone Recommendations experiment.
Or learn about augmenting Recommendations with Experimentation and Personalization.
Ideas for recommendations
There are many ways to use recommendations on your site. Below, we suggest a few retail and B2B use cases.
In the checkout funnel, show accessories that complement the items a visitor is purchasing
On product detail pages, show alternative items that are related to the product a visitor is browsing
Highlight crowd favorites on the homepage
If you're using Optimizely X to test on a checkout page, you might need to configure your site for PCI compliance. See this article for details.
B2B or lead generation sites:
Show visitors whitepapers, infographics, blog posts, and other content based on their browsing behaviors
Suggest knowledge base articles or community posts to reduce support call volume
For more ideas, join the conversation in Optiverse Community.
Optimizely offers five algorithms for recommendations.
Co-browse: "Website visitors who viewed this product also viewed these other products."
Consider this algorithm for high-price catalogs, where a visitor is unlikely to purchase more than one item at a time.
Co-buy: "Website visitors who bought this product also bought these other products."
This algorithm is great for low-price checkout funnels, where visitors are likely to purchase complementary products or add several items to an order.
Popular Items: "Items that website visitors most frequently viewed or bought."
This algorithm helps showcase crowd favorites on the homepage. Use it to introduce best-selling items to new visitors.
Recently Viewed: "Items that you previously browsed."
This option helps you remind visitors of items they've already shown interest in.
User-based: "You browsed similar products as this group of website visitors, and they tended to like these products."
This algorithm is based on user IDs (rather than item IDs, like co-browse). Because user-based recommendations are based on visitors, you can show them on any page of the site for a personalized experience.
Recommendations are generated every 24 hours. So, the catalog information may be up to 24 hours stale, with a mean of 12 hours.