Create a recommender

Updated Nov 8, 2026 Based on Salesforce docs and web research updated 2026-11-08

A recommender returns items from your content schema’s catalog, ranked toward a goal you pick — for example “customers who viewed this also viewed” or “trending now.” A decision calls the recommender to fill its response.

Create the recommender

  1. From Personalization setup, create a new recommender.
  2. Choose objective-based if you want Personalization to rank items using machine learning toward a goal such as Maximize Revenue or Maximize Clicks.
  3. Make sure the fields that objective needs are present on your item data graph — an objective-based recommender can’t optimize toward data it can’t read.
  4. Save the recommender, then attach it to a decision so a personalization point can serve its results.
Recommender setup screen showing the objective-based type and its objective
Screenshot: Recommender setup

Discussion

Comments are not configured for local development. They appear once the site owner connects GitHub Discussions (Giscus).

Support SF Guide

SF Guide is a free, independent guide to Salesforce Personalization, built and maintained in the open. If it saved you time on an implementation, a small contribution helps keep it current and ad-light.