Recommendations

You can apply recommendations in Optimizely in two ways: use the audience functionality, or add the recommendation capabilities included with Optimizely Product Recommendations.

By applying machine learning and statistical analysis to behavioral data, the platform utilizes visitor behavior to autonomously create and optimize individual content and product views.

The native integration for Commerce Connect is part of Optimizely Product Recommendations, a suite of cloud-based products combining machine learning, artificial intelligence, and statistical analysis. You also need an Optimizely Product Recommendations environment to receive tracking data and serve recommendations. See also Product recommendations (for Commerce Connect).

Key integration components for recommendations

Recommendations have key components that you should not alter. If you need to alter the following components, coordinate with Optimizely.

User tracking

Changes to user tracking needs can result in loss of behavior and core functionality — for example, switching from tracking plain email addresses to pseudonymized user IDs or the reverse.

Recommendations – To prevent user behavior from being lost, send Optimizely an up-to-date mapping between email addresses and pseudonymized user IDs. Provide it once so that Optimizely Recommendations can replace existing customer email addresses with the corresponding pseudonymized user ID.
Mail – Continually provide your Email Service Provider (ESP) with an up-to-date mapping between email addresses and pseudonymized user IDs. The ESP creates a placeholder (mail merge variable) that represents the pseudonymized user ID. Then replace the email address placeholder in all your Mail campaigns with this placeholder.
Triggers – Your ESP must handle pseudonymized user IDs. In Triggers, this functionality is provided only by Optimizely Campaign. Alternatively, advise your ESP to provide an API extension that lets Optimizely call methods that accept the pseudonymized user ID instead of an email address. Also, provide and maintain a mapping between pseudonymized user ID and customer email address that your ESP can use as a lookup to send the email to the appropriate customer based on the pseudonymized user ID.
Promote – If provided, Recommendations can use the visitor's IP address within their session to do a geolocation lookup to identify the approximate location of the visitor for a personalized online experience. IP addresses, if provided, are no longer stored, so they cannot be used for analytics and reporting.

When you provide and test a user mapping, coordinate with Optimizely to schedule a deployment and receive further instructions.

Product reference

The product reference (productId) is a crucial connector between your data and the Optimizely recommendations engine; changes to this identifier break the connection between collected behavior and your product catalog. To prevent this connection from breaking, inform Optimizely of any plans to change the format of product references in your feed and tracking implementation. Provide a mapping from the old to the new product references and coordinate a deployment with Optimizely.

Known limitations

If Optimizely ServiceApi and Optimizely Recommendations are installed in parallel, this imposes the following limitations on recommendation functionality:

Client-side tracking is not supported, and user changes cannot be detected.
Although the catalog feed export works without limitation, the utility action for locally downloading the latest feed (/episerverapi/downloadcatalogfeed) requires token authentication. For information, see Install and configure – Service API > Configuring OWIN startup.

To avoid these limitations, install the Service API in a separate application.