Implementation Steps

Overview

Recommend is powered by the Algonomy's Omnichannel Personalization Cloud, which ingests robust sets of data on individual shopper behaviors and customer micro-trends on an ongoing basis for each merchant site. Leveraging this data, the Cloud routinely builds recommendation models that internalize product affinities, shopping patterns, inventory, pricing, and more. These learnings are output as over 100+ strategies that support a variety of business objectives. As shoppers continue to interact with the site and recommendations, Recommend self-optimizes---the solution displays the most performant strategies and contextually-relevant product sets that drive sales conversion.  Recommend is supported by comprehensive merchandising controls that enable you to influence the display and content of recommendations.

This intended audience of this document includes Retailers who implement Recommend on their websites and understand the steps required and the roles/skills needed to implement Recommend. For more information about the procedure to implement Recommend, see developer documentation. 

Recommend is a powerful tool that enables retailers to drive personalized recommendations in key locations on their site to their customers, bringing them relevant products that help to bring about improved retail performance.

Implementation of a product like Recommend requires careful thought and the right resources to make sure that the instrumentation goes smoothly. Recommend ingests data from the retailer in various Feeds that it uses to recommend products to end-users in placements on the retailer's website, using a complex mix of strategies, rules, and an engine that continuously works to display the most relevant recommendations in real-time.

Implementation and Instrumentation

Many of the documents required to implement Recommend can be found in this guide. The details of integrating Recommend features are available in the Feature Integration: Recommend Features.

Integration

Once you have reviewed the content in the Integration Overview, you will want to review the Integration Overview Guide to better understand the basics of client-side and server-side integration.

When you are ready to begin the instrumentation of your site, you will use either the Javascript Integration (for client-side) or you will use API calls (for client & server-side). At its core, instrumentation is the action that adds code to your existing site on relevant pages where Algonomy will observe the click stream of the customer and then deliver personalized recommendations.

This is the first step. Once the instrumentation is complete, it is time to add placements and layouts, implement necessary Merchandising Rules, set up Strategy messaging, and other tasks that get your site ready to deploy recommendations. You will work with your Algonomy team throughout this process to ensure that your instrumentation and implementation are completed efficiently and effectively.

General

Recommend Best Practices - This guide, and the articles it contains, is a good place to begin understanding how to get the most from your Recommend implementation.

Strategies

Recommendations Strategies Guide - This document gives an overview of how the Personalization Cloud works, examples of custom messaging, and a listing of strategies by type.

Listen Mode

A Guide to Early Recommendation Quality - This document aims to address some of the common questions that are raised regarding the quality/relevance of recommendations during the early stages of an implementation project, in particular during Listen Mode, but also during the early weeks of Live Mode.

Live Mode

Performance Reporting - A Metrics and Reporting guide covering the Sales and Site Analytics areas of the Reporting section.