Skip to main content

Einstein Recipes: Interaction Studio’s Secret Ingredient

It’s no secret companies are watching their customers more than ever, gathering data, analyzing trends, and utilizing that information to serve personalized experiences that drive engagement. 

We’ve all been there — hovering over the “Proceed to Checkout” button in an online shopping cart when a product recommendation catches your eye. On impulse, you add it to your cart before continuing to checkout. There’s a good chance that experience was powered with a tool in Interaction Studio — Einstein Recipes

This blog will walk through what Einstein Recipes are, and when, where, and how to use them. 
 

What Are Einstein Recipes?

One of Interaction Studio’s most powerful features is Einstein Recipes. These machine-learning powered algorithms curate content based on the “ingredients” selected by the business user to be returned in the form of a recommendation on site, in emails, or even in a mobile app. When strategically placed, these suggestions will increase cart value and encourage continued engagement. 

Recipes are most often used in the ecommerce realm for recommending products, and in B2B and financial services for recommending content (blogs, articles, services, etc.).  The recipe ingredient options reflect these uses. 

The recipe itself is simply the algorithm. Recipes are referenced in Interaction Studio templates that define how the individual recommendations should look.

 

When and Where to Use Recipes 

Before building a recipe, it’s important to define when and where they will be used. When a recipe is used can alter which ingredients will be the most powerful. Recipes that require a more robust view of the user would be best utilized in a campaign that doesn’t show until the second or third visit or until a user lands in the checkout flow. On the flip side, a campaign running on the homepage for new users could simply show trending products. 

Some examples of strong recipe use cases are:

  • “Pick up where you left off” on the homepage — displays items previously viewed by the user
  • “Popular Now” on the homepage — displays items viewed, purchased, or favorited the most
  • “You may also like…” on a PDP (Product Detail Page), Out of Stock, or cart page — displays items users like you also like
  •  “More like this” on a PDP — displays items frequently viewed or purchased together
  • “Complete the collection” on a PDP or cart page, displays items specifically linked together as a set
  • “What’s New?” on the homepage — displays most recently published items
  • “Get Free Shipping” on a cart page — displays items to help a user reach the free shipping threshold

While the examples above all reference an item recommendation, Interaction Studio templates can be configured to return other recommendations aside from the classic built-in product, article, and blog items. Other unique custom items that could be utilized in a recipe include: Brand, Color, Size, Author, Industry, etc. A helpful way to think about these other options is “What can my customers build an affinity to?”

Take advantage of Interaction Studio’s campaign/experience system, and create multiple recipes to A/B test them against each other. 
 

Recipe Outcomes

The intended outcome of an Einstein Recipe is clear: encourage the customer to consume more. More specifically, in the ecommerce realm, recipes aim to cross-sell, upsell, and keep the customer coming back for their tailored experience. For finance, B2B, and service industries, recipes aim to increase engagement, keep the customer onsite longer, and influence their decisions.

When served correctly, Einstein Recipes will keep users coming back for seconds. In the next part of the Einstein Recipe series I will dive deeper into the technical aspects including testing and optimizing.