Implementation

Overview

This document defines the HTML instrumentation and parameter syntax of the email campaign as required by Algonomy’s recommendation engine. This information is intended for the associates who want to understand how to populate values in an ESP template.

Recommend enhances emails by displaying relevant, targeted product recommendations on a customer-by-customer basis, driving site visits and higher sales while strengthening customer relationships. It seamlessly integrates into your existing email campaigns and automatically generates product recommendations targeted towards specific marketing and merchandising objectives.

Each ESP has a different process for going live. Ensure to understand the requirements before getting started. Ensure that you are familiar with HTML and JavaScript and you have a background in the ecommerce/retail industry.

At a high level, the HTML “stub” which lives in the email source, gets populated by the ESP with several product-related and customer-related fields in the image source and image map HREF parameters.

  • When the customer opens an email containing Algonomy HTML, an image request is made to the recommendations platform, passing parameters such as Order ID, Customer ID, and Product ID(s).

  • Algonomy sends back the recommended products as an image map. The image is built by applying an HTML template to product data and returned to the customer’s email.

  • Upon image generation, Algonomy tracks which products were recommended, caches the image, and stores the matching clickthrough URLs for products in each position in the image. The cached images last for 48 hours, after which new products will be recommended for a new open.

    Note: Cached images do not carry across layouts. For example, if a site has a mobile layout and desktop layout for the same placement, and the customer initially enters through mobile, when they open their email through the desktop, new products will be recommended.

Introduction

Recommend enhances emails by displaying relevant, targeted product recommendations on a customer-by-customer basis, driving site visits and higher sales while strengthening customer relationships. It seamlessly integrates into your existing email campaigns and automatically generates product recommendations targeted towards specific marketing and merchandising objectives.

Algonomy targets recommendations to individual users by tracking and evaluating multiple aspects of shopping behavior: a user’s browse and purchase history, emerging customer trends unique to each retailer, group behavior, and more. The technology then selects the best recommendation type to display from over 60+ different options, each with descriptive message that communicates to customers for the recommended products. Integration is fast and easy and accomplished with the simple addition of tracking code to your site (not necessary if you already run Recommend), and copying/pasting a few lines of HTML into the templates of selected email campaigns.

Typically, retailers start using Recommend email to add recommendations to transactional emails, like order confirmation, shipping confirmation, and abandoned cart notifications. Recommend email can also be used in promotional emails wherein you establish the context of the promotion (using variables defined later in this guide) and Recommend returns appropriate recommendations with the email.

Recommend enables you to control all aspects of your email campaigns including messaging, look and feel, and filtering capabilities. We also provide full reporting on campaign performance with specialized data such as number of opens, open date, click thru rate, and sales

Step 1: Website (one-time)

Note: If Recommend is already installed on your website, you can skip to Step 2.

Integrating Recommend into email starts by placing JavaScript tags on select pages of your website , so Algonomy can collect the product and behavioral data necessary to serve targeted recommendations in email. Contact your Client Services team to get your website set up.

Step 2: Email Setup (per recommendation in email look and feel)

After you identify which email campaigns to add recommendations, you need to copy/paste your Algonomy-generated HTML into your email templates for personalized product recommendations to display when opened. For detailed information about setting up the email, see How-To: Set up Responsive Layout Email Solution.

Note: If the ESP grants us the ability to trigger test emails, Algonomy can handle this step.

All the steps up to this point are performed in an integration environment. Once Algonomy has sign-off, we will migrate the layout to the production environment and make any necessary changes to the Algonomy markup in the email template. Once we have sign-off on the HTML customizations from the merchant and ESP, we will go live in production.

Note: Each ESP has a different process for going live.

Parameters

The tables found on the How-To: Set up Responsive Layout Email Solution page, detail the various parameter names, descriptions and whether or not the parameter is required in the email's HTML when implementing Recommend + Email.

Email User Identification

For email, the recipient's User ID is included on the click URL. To leverage this, the ID needs to be passed through the click URL upon click using the parameter 'u'. The intent is to strengthen the personalization and connect the customer’s email actions with their overall User Profile.

Follow the below steps for Email User Identification:

  1. In Site Configurations RR (required to access and complete by a member of the Algonomy team), find the configuration "enable email user identification."

  2. Select the checkbox next to "enable email user identification." This will pass the user ID whether or not that retailer is logged in to their client account.

  3. Once selected, approve and publish to enable in production.

  4. If the 'u' parameter has a non-empty value, that value will be passed. It is not necessary to do anything.

    Notes:

  • This configuration is disabled by default. In any case where a client using email wants to leverage this, the site configuration needs to be enabled.

  • Do not manually pass the parameter 'rr_u' - this happens automatically if necessary. If you manually pass the parameter, it causes the site configuration to be ignored and is not a proper use of the feature.

Reporting

Recommend Email provides a robust reporting dashboard for marketing managers to review performance of their email campaigns. We also provide multiple ways to filter and look at performance across custom date range, various performance metrics, different email campaigns, and even by specific strategy families. Here are the filtering options available:

Date Range:

  • Weekly

  • Monthly

  • Yearly

  • Custom Date Range

Metric:

  • Impressions: Rendered emails containing Algonomy recommendations

  • Clicks: Clicks on products in recommendation placements

  • Rec Click Thru Rate: Clicks on recommendations as a percentage of impressions

  • Total Campaign Sales: Overall site-wide sales from users coming onto the site after clicking Algonomy recommendations in emails. The attributable window is configurable to match your marketing objectives (default = 7 days).

  • Total Campaign Orders: Overall orders attributable to recommendations in emails.

  • Total Campaign Items: Overall product units sold site-wide, attributable to recommendations in emails

Campaign:

  • List of campaigns that have run for the site

  • Cross-campaign comparison for a given metric

Strategy:

  • Reporting on strategy family performance for email campaigns

  • Capability to drill down and look at performance by specific strategies as well.