Products: Product Sets

What are product sets in Spotler Activate?

Product sets in Spotler Activate are dynamic collections of products defined by rules such as category, price, brand, or availability. These sets automatically update as your product catalog changes and is used for personalization and marketing campaigns. Spotler Activate offers different types of product sets, each based on behaviour, purchases, or product data, used for personalization and recommendations.

Example of products

1. Sale products
   Rule: Discount > 20%
   → Always shows current sale items
2. Category bestellers
   Rule: Category = Electronics Sort: Popularity
   → Automatically keeps top performers
3. Seasonal collections
   Rule: Tag = Summer
   → Updates as new seasonal products are added

We have created a number of standard product sets. You can recognize automatically created sets by the magic wand icon. The following product sets are automatically composed for profiles: 

In this article:

• Why product sets matter?
• New product set
• Selection methods
• Fallbacks

How product sets work (simple explanation)

Step 1: Define rules

You create a product set using filters like:

• Category (e.g. Shoes)
• Brand (e.g. Nike)
• Price range
• Stock availability
• Custom attributes

👉 Example:
“Include all products where category = Running Shoes AND price < €100”

Step 2: Products are automatically included

Any product that matches your rules is added to the set.

Step 3: Sets update automatically

• New matching products → added
• Products no longer matching → removed
• Out-of-stock or changed products drop out

No manual updates needed.

Step 4: Use across campaigns

Product sets can be used in:

• Email campaigns
• Website personalization
• Automated flows
• Product recommendations

Why product sets matter

Automation

No manual product selection required.

Personalization

Combine product sets with user behavior:

• Viewed products
• Preferred categories
• Purchase history

Consistency 

Use the same product logic across multiple channels.

FAQ's

New Product Set

Custom product sets can be created based on selection methods and filters. You can create these product sets by clicking on New Product Set. You create a product set on the basis of selection methods:

• Recommenders: Spotler Activate analyses patterns in the events of profiles and uses these for the recommenders:
  • Recommended for you
  • Items you may like
    
    Note: Creating or editing the recommenders can take a few minutes, since the set for each profile needs to be calculated.
     
• Events: based on events, sets can be compiled such as:
  • Last viewed 
  • User behavior
    
    Note: If an existing set is changed on the basis of events, this set is emptied for all profiles.
     
• Other: the following sets are available based on purchase and inventory:
  • Most sold
  • Most in stock

Selection methods

In this section you read more about the selection methods in Spotler Activate and what the difference is between them:

• Items you may like
• Recommended for you 
• What is the difference between "items you may like" and "recommended for you"?
• User behavior
• Last viewed
• Most sold
• Most in stock
• What is the difference between product sets? 

Items you may like

What is "Items you may like?" 

The Items you may like product set recommends products based on behavioural similarity between profiles.

It suggests products that other profiles have:

• viewed
• added to their basket
• purchased

after interacting with the same product.

Events used

• ViewContent
• AddToCart
• Purchase

How it works (simplified example)

To explain the logic, this example only uses the ViewContent event. 

Input: Profile A

Profile A has viewed:

• Product 1

Input: Other profiles

Profiles who also viewed Product 1:

• Profile B → Products 1, 2, 3
• Profile C → Products 1, 3
• Profile D → Products 1, 2, 3, 4

Output: Items you may like (ranked)

1. Product 3
   → Viewed by all 3 profiles
2. Product 2
   → Viewed by 2 out of 3 profiles
3. Product 4
   → Viewed by 1 profile

Key idea

👉 “Items you may like” is based on behaviour similarity across users

Options

The following extra options can be applied to the composition:

• Max # of products: the maximum number of products in the set (when the maximum number is reached, the product that was first in the set goes first)
• Exclude product set: products from another product set can be excluded for this product set
• Exclude # last recommended: the number of recently recommended products is excluded for this product set, so that the same products are not shown constantly
• Recency weight: the extent to which more value is attached to recently viewed products
• Recommend based on products: the recommendations are compiled based on the product id that is sent along in the event instead of the profile's behavior
  
  Example recommend based on products
  When you select this option, it is obligatory to send a product id in the event when composing the product set. The set will be composed based on the product id which is sent. So the relations of the product with other products is specifically looked at, instead of the total behaviour of the profile towards products.

• Fallback set: if insufficient products meet the criteria to reach the maximum number of products, the product set can be supplemented with products from another product set.

The set can be specifically or dynamically composed with: Product Set Filters

Recommended for you

What is “Recommended for you”?

The Recommended for you product set suggests products that are frequently purchased together. It recommends products that other profiles bought in the same order as the product a profile interacted with.

Event used

• Purchase

How it works (simplified example)

This process runs at scale across all profiles and products, where time and weighting influence the final ranking.

Input: Profile A

Profile A has added:

• Product 1 to the cart

Input: Other profiles
Profiles who purchased Product 1:

• Profile B → Products 1, 2, 3 
• Profile C → Products 1, 3 
• Profile D → Products 1, 2, 3, 4

Output: Recommended for you (ranked)

1. Product 3
   → Purchased together by all 3 profiles 
2. Product 2
   → Purchased together by 2 profiles 
3. Product 4
   → Purchased together by 1 profile

Key idea

👉 “Recommended for you” is based on products frequently bought together

Options

The following additional options can be applied to the composition:

• Max # of products: the maximum number of products in the set (when the maximum number is reached, the product that came first in the set goes first)
• Exclude product set: products from another product set can be excluded for this product set
• Exclude # last recommended: the number of recently recommended products is excluded for this product set, so that the same products are not shown constantly
• Recency weight: the extent to which more value is attached to recently viewed products
• Recommend based on products: the recommendations are compiled based on the product id that is sent along in the event instead of the profile's behavior.
  
  Example recommended based on products:
  When you select this option, it is obligatory to send a product id in the event when composing the product set. The set will be composed based on the product id which is sent. So the relations of the product with other products is specifically looked at, instead of the total behaviour of the profile towards products.
• Fallback set: if insufficient products meet the criteria to reach the maximum number of products, the product set can be supplemented with products from another product set.

The set can be specifically or dynamically composed with: Product Set Filters.

What is the difference between "items you may like" and "recommended for you"?

The main difference is that “Items you may like” is based on user behaviour (such as views and clicks) across similar profiles, while “Recommended for you” is based on products that are frequently purchased together in the same order.

User behavior

What is “User behavior”?

The User behavior product set is a flexible set that allows you to define which product interactions are used for recommendations.

You can use any event that includes a product ID, including:

• standard events
• custom events

How it works

Products are added to the set based on interactions of a specific profile.

This means:

• the set is fully personalized
• the logic depends on the selected event(s)

Key idea

👉 “User behavior” is based on custom-defined interactions per profile

Options

The following additional options can be applied to the composition:

• Retention: the number of days the products remain in the set after the interaction with the product
• Max # of products: the maximum number of products in the set (when the maximum number is reached, the product that came first in the set goes first out)
• Fallback set: if there are not enough products that meet the criteria to reach the maximum number of products, the product set can be supplemented with products from another product set.

Last viewed

What is "Last viewed" 

The Last viewed product set contains the most recently viewed products of a profile. It is based purely on the browsing behaviour of that specific user.

Event used

• ViewContent

How it works

Each time a product is viewed:

• it is added to the set
• the most recent products are prioritized

Key idea

👉 “Last viewed” is based on recent browsing behaviour

Options

The following additional options can be applied to the composition:

• Retention: the number of days the products remain in the set after viewing the products.
• Max # of products: the maximum number of products in the set (when the maximum number is reached, the product that came first in the set is removed first).
• Fallback set: if there are not enough products that meet the criteria to reach the maximum number of products, the product set can be supplemented with products from another product set.

Most sold

What is " Most sold"?

The Most sold product set contains the best-selling products from the past 7 days. It is based on the purchase behaviour of all profiles and reflects overall product popularity.

Event used

• Purchase

How it works

All purchases from the last 7 days are analyzed.

Products are ranked based on:

• number of purchases
• overall popularity across all profiles

Key idea

👉 “Most sold” is based on global popularity (not personalized)

Options

The following additional options can be applied to the composition:

• Max # of products: the maximum number of products in the set
• Fallback set: if not enough products are sold to reach the maximum number of products, the product set can be supplemented with products from another product set

Most in stock

What is "Most in stock?" 

The Most in stock product set contains the products with the highest available inventory. It is based on product data rather than user behaviour.

Product field used

• Inventory

How it works

Products are ranked based on:

• current inventory levels

The products with the highest stock are included in the set.

Key idea

👉 “Most in stock” is based on inventory levels (not behaviour)

Options

The following additional options can be applied to the composition:

• Max # of products: the maximum number of products in the set
• Fallback set: if insufficient products are in stock to reach the maximum number, the product set can be supplemented with products from another product set

What is the difference between product sets? 

Fallbacks

What happens if there is no data?

Fallback logic ensures that product sets always contain relevant items, even when there is limited or no data available.

Common scenarios

• New users
  If a profile has no interaction history, the fallback set is used to display products.
• New products
  Products are included in recommendations once relevant events (such as views or purchases) are recorded.
• No matching products
  If no products meet the criteria of the product set, the fallback set is used to fill the remaining slots.

Why fallbacks matter

• Prevent empty content blocks
• Ensure a consistent user experience
• Increase conversion (always show something relevant)

Examples:

• No personal data available → Show: Bestsellers
• No products in set (e.g. out of stock) → Show: Alternative category
• Too few items (e.g. < 4 products) → Fill with: General recommendations

Possible fallback sets

A product set is based on a selection method and (possible) fallback sets. For more information about the composition of the sets click on the selection method.