Last updated: Feb 05 2019
Episerver Personalization developer guides
Episerver Personalization is a suite of cloud-based products, combining machine learning, artificial intelligence, and statistical analysis.
Personalized content recommendations online.
Personalized product recommendations online.
Personalized email recommendations and message triggers.
Personalized search results.
As part of the onboarding, Episerver sends the required configuration keys and credentials to the technical contact for your project. Use the keys to configure the tracking for your websites. Contact Episerver for questions regarding the onboarding process.
The Episerver Personalization suite is based on a tracking component, a core personalization system, and general or product-specific integrations. The personalization system has a recommendation service that is fed with visitor tracking data from CMS, Commerce, and Find. The personalization engine processes visitor data and predicts intent.
Based on this, recommendations are provided for content - Episerver Advance, products - Episerver Perform, and search results - Episerver Personalized Find. The tracking data can be stored in Episerver Profile Store (Customer Data Platform), or any other source. Episerver Insight is used for visualizing and analyzing profile data.
To get the personalization running for a site, you need to configure the access to the tracking API, so that you can post usage data and get recommendations back.
Native integrations provide Episerver product-specific access to the core personalization Server-to-Server API for managing JSON tracking data and JSON-formatted content. It is recommended to use native integrations for the Episerver platform, to simplify implementation of basic tracking and the product catalog feed. See Native integrations.
The Server-to-Server API lets you integrate any website or application with products in the Episerver Personalization suite. In response to the tracking data sent, recommendations are returned with the Server-to-Server API response payload, based on JSON tracking data and JSON-formatted content. See Server-to-Server API.
Widgets and recommendations
A widget is a block displaying recommendations, either on a web page or in an email message. Widgets provide an automated way to add recommendations based on visitor interaction and other visitors' purchasing behavior. The recommendations are configured in the strategy defined for each widget, and are calculated by specific algorithms based on visitor tracking data.
During onboarding and personalization implementation, Episerver works with the customer to define KPIs and recommendation strategies, and customize algorithms based on this. Widgets are set up for example for the "home" and "product" pages, and recommendations will be automatically served based on these default configurations. This default "product strategy" can be manually overridden from the Personalization Portal, by "handpicked" strategies.
The Episerver Personalization suite is based on a service, and a set of NuGet packages providing access to the APIs.
The service onboarding and solution setup typically involves these steps:
- Analyze requirements, define recommendation strategy and integration method.
- Install and configure service and components, set up test environment.
- Export product catalog feed, review and adjust.
- Implement tracking, create content types, templates, and widgets.
- Work with conversion data and merchandising rules in the Personalization Portal.
- Deploy, test and adjust the setup.
See Install and configure personalization how to install and configure the NuGet packages needed to access the API, and start working with personalization.
- Install and configure personalization
- Native integrations
- Data import guides
- Personalization API
- Personalization Portal