Contextual Algorithms

  • Updated on Oct 1, 2025
  • Published on Jan 21, 2021
  • 8 minute(s) read
Prev Next

In Contextual Algorithms, product recommendations are based on the immediate context of individual consumers, such as the category of the product page they are browsing. While these algorithms do not take into account a consumer’s past behavior or activity, they tailor recommendations to the situation at hand, increasing relevance in the moment.

The algorithms covered under Contextual Filtering are:

Viewed Together

The Viewed Together algorithm generates recommendations based on the products visited in the same sessions and the same locale (the language of the website that the user visits) during the selected lookback period. After generating recommendations, the results are arranged according to their visit frequency or popularity. This way, users can discover complementary or alternative products related to the one they currently view. This increases discovery rates and the chance to grab users’ attention when they don’t have a target product.

  • Available Channels: Web Smart Recommender and App Smart Recommender
  • Page Type: Product/Article Page, Cart Page
  • Example Use Case: Showing items that have grabbed visitors' interest during previous sessions can bring the visitors closer to adding the viewed or recommended products to their cart and eventually increase conversions.
  • Fallback Algorithms: Most Popular of the Category, Most popular items
  • Prerequisites: 30 days of product views
  • Maximum Number of Products to Recommend (in the same variant): 50

Purchased Together

The Purchased Together algorithm generates recommendations based on products purchased in the same sessions and in the same locale (the language of the website visited by the user) during the selected lookback period. After generating recommendations, the algorithm orders the results according to the purchase frequency of each item. With this algorithm, you can apply the purchase patterns of their users to their strategies.  

  • Available Channels: Web Smart Recommender and App Smart Recommender
  • Page Type: Product/Article Page, Cart Page
  • Example Use Case: Expanding the user's cart amount by showing products that have been bought together by other users and increasing cross-category selling options. With a feeling of “Users who purchased this item also purchased…”, you can utilize both the impact of product popularity and the preferred price-quality balance on your users.
  • Fallback Algorithms: Top Sellers of Category, Top Sellers
  • Prerequisites: 30 days of product purchase.
  • Maximum Number of Products to Recommend (in the same variant): 50

Location-based Top Sellers

The Location-based Top Sellers algorithm enables you to deliver personalized product recommendations to each website visitor. It analyzes a user's current location (IP address geo-location) and serves the most sold products in that location.

  • Available Channels: Web Smart Recommender and InStory
  • Page Type: Home Page, Product/Article Pages, Category Pages, Cart Pages
  • Example Use Case: Display products that enable the user to complete the discovery, add-to-cart, and purchase flow. Especially for local products and demographic trends (e.g., student populations around campus), you can increase purchase rates with the help of geographically personalized recommendations.
  • Fallback Algorithms: Top Sellers of the Category, Top Sellers
  • Prerequisites: 30 days of product purchase data.
  • Maximum Number of Products to Recommend (in the same variant): 90

Checkout Recommendation

Taking the basket amount into account, the Checkout Recommendation algorithm recommends only the products that fulfill the campaign amount, along with the Purchased Together algorithm. Since it operates based on the total price of the items the user has added to their cart, this algorithm is suitable for Web Smart Recommender and App Smart Recommender.

When you choose "Checkout Recommendation" as the recommendation strategy, set the basket amount in the Campaign Price field of the Smart Recommender Strategies.

For example, if a user has two items in their basket totaling 100 USD, and there is a free shipping campaign for orders exceeding 150 USD, the system will recommend items that cost at least 50 USD to reach the required amount. However, if the user's basket amount already exceeds 150 USD, no product recommendations will be made.

  • Available Channels:Web Smart Recommender and App Smart Recommender
  • Page Type: Cart Page
  • Example Use Case: In cart pages, to increase AOV, you can organize some campaigns, such as free shipping campaigns - "Order at least X USD, get free shipping". Considering the basket amount, only products that fulfill the campaign amount are recommended with the Checkout recommendation.
  • Fallback Algorithms: NA
  • Prerequisites: NA
  • Maximum Number of Products to Recommend (in the same variant): 90

Most Popular Items of the Category

The Most Popular Items of the Category algorithm generates recommendations based on page view counts during the last 30 days in the same locale (the website's language that the user visits). The Most Popular Items of the Category algorithm operates with the same logic but generates results from the same category as the product or category currently being viewed. After generating recommendations, the algorithms order the results in descending page view counts and place them on the smart recommender widget.

  • Available Channels: Web Smart Recommender, App Smart Recommender, and InStory
  • Page Type: Product/Article Pages, Category Pages
  • Example Use Case: Display the most popular products and promote the hottest ones that have been viewed or sold the most on the website. Display products that capture users' attention within the same category, and apply filters to highlight products with higher prices, creating upsell opportunities across the same category and other categories.
  • Fallback Algorithms: Most Popular of the Parent Category
  • Prerequisites: 30 days of product views.
  • Maximum Number of Products to Recommend (in the same variant): 90

Most Valuable Items of the Category

The Most Valuable Items of the Category algorithm recommends products that generate higher revenue across your site, considering both the contribution to revenue and revenue per visit. All users see the same recommendation.

  • Available Channels: Web Smart Recommender, App Smart Recommender, and InStory
  • Page Type: Product/Article Pages, Category Pages
  • Example Use Case: Promote more revenue-generating products on your website. 
  • Fallback Algorithms: Most Valuable Of Parent Category
  • Prerequisites: "Product Value Scoring" and "Most Valuable Products" should be enabled so your account can use the Most Valuable Products algorithm.
  • Maximum Number of Products to Recommend (in the same variant): 90
It is recommended that you select a minimum look-back period of 3 days to ensure accurate recommendations for products with higher revenue.

Substitute Products

The Substitute Products algorithm recommends similar products, and it helps the product discovery process. The Substitute Products algorithm considers product similarity and price proximity.

  • Available Channels:  Web Smart Recommender
  • Page Type: Product/Article Page, Cart Page
  • Example Use Case: Identify substitute products that can be purchased in place of each other. Substitutable products are interchangeable, such as one T-shirt for another.
  • Fallback Algorithms: Viewed Together, Most Popular of the Category
  • Prerequisites: The price of the items recommended should be within 0.5-1.5x.
  • Maximum Number of Products to Recommend (in the same variant): 90
We do not recommend using this algorithm unless the item prices are within a 0.5- to 1.5-fold range.

Complementary Products

The Complementary Products algorithm employs a distinctive approach to offering product recommendations that complement users' existing preferences and purchases. It examines products frequently bought together or identified as complementary through user interactions, proposing items to enrich users' overall shopping journeys. It considers item performance when creating complementary products.

  • Available Channels:  Web Smart Recommender
  • Page Type: Product/Article Page, Cart Page
  • Example Use Case: Complementary products are items that are typically purchased together because they enhance or complement each other’s use. For example, a laptop and a mouse are considered complementary products.
  • Fallback Algorithms: Purchased Together, Top Sellers of the Category
  • Maximum Number of Products to Recommend (in the same variant): 90

Recently Viewed Items

The Recently Viewed Items algorithm is one of the personalized algorithms. It tracks the user’s product view behavior, which is collected from the Unified Customer Database (UCD). It means it collects data from both Web and Mobile events.

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Available Pages, Product/Article Page, Cart Page, All Pages, Category Page
  • Fallback Algorithms: NA. We highly suggest using a combination of products and enabling the “Hide the recommendation if there are not enough products to recommend” option. If you want it to be displayed in all cases(when the Hide option is not selected), then when a new (or non-login) user displays even a single product, the widget will be visible with that product. 
  • Example Use Case: On the cart screen, you can display the user’s recently viewed products, increasing the AOV through the end of the purchasing funnel.
  • Prerequisites: Having product view activity in the last 30 days.
  • Maximum Number of Products to Recommend (in the same variant): 50

This algorithm is updated once a user visits a new product, and the update is reflected in the UCD. It takes the last 30 days of activity. Products viewed before this period are not taken into consideration. The user’s previous product views, as well as the current session views, are combined in the algorithm. 

You can shuffle the recommendations. However, if you do not shuffle them, the most recently viewed product is displayed first. Insider filters exclusions on the Smart Recommender are available, except for the "Exclude Recently Viewed Items" option, as its primary purpose is to track this specific event (Web and API-based only).

For the App Smart Recommender, filters and exclusions are limited to the App Smart Recommender’s capabilities.

Purchased with Last Purchased

The Purchased with Last Purchased algorithm is one of the personalized algorithms. It recommends products purchased in conjunction with the user’s most recent purchase. Purchase events can be collected from Web, Mobile, and Offline (CRM) UCD events.

  • Available Channels: App Smart Recommender and InStory
  • Page Type: All Available Pages ( Product/Article Page, Cart Page, All Pages, Category Page)
  • Fallback Algorithms: Top Sellers of the Category, Top Sellers
    • Top Sellers of the Category is the primary fallback. It uses the Category that the user is browsing at the moment of recommendation creation.
    • If the user is not in a specific category, the algorithm will use the secondary fallback, the “Top Sellers.”
  • Example Use Case: To personalize a page, you can display products purchased together by the user’s last purchase.
  • Prerequisites: 30 days of product purchase.
  • Maximum Number of Products to Recommend (in the same variant): 50

The algorithm takes the latest purchased product ID and creates recommendations based on this item (A single product). It checks if there is a purchase in the last 30 days. Products purchased before this period are not taken into consideration.

Insider's filters and exclusions are available on the Smart Recommender (Web and API-based only). However, the App Recommender's filters and exclusions are limited to its capabilities.

Related articles