Generic Algorithms

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

In Generic Algorithms, product recommendations are based on product performance rather than individual consumer behavior or current context. These algorithms prioritize items that perform well overall, assuming that the most popular or frequently interacted-with products are likely to appeal to a broader audience. This makes them especially useful in scenarios where little or no user-specific data is available.

The algorithms covered under Generic Algorithms are:

Most Popular Items

The Most Popular Items algorithm generates recommendations based on page view counts during the selected lookback period in the same locale (the website's language the user visits). The Most Popular Items of the Category algorithm operates on the same logic, but it retrieves results from the same category as the product or the 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, InStory, and Email
  • Page Type:
    • Most Popular Items: All Pages, Product/Article Pages, Category Pages, Cart Pages
    • Most Popular Items of the Category: 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: Top Sellers of Parent Category
  • Prerequisites: 30 days of product views and at least 100 in-stock products
  • Maximum Number of Products to Recommend (in the same variant): 90

Top Sellers

The Top Sellers algorithm generates recommendations based on purchase counts during the selected lookback period in the same locale (the website's language that the user visits). Top Sellers of the Category works with the same logic but brings results from the same category as the product or category that is currently being viewed. After generating recommendations, the algorithms order the results in descending purchase counts and place them on the Smart Recommender widget.

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: 
    • Top Sellers: All Pages: All Pages, Product/Article Pages, Category Pages, Cart Pages
    • Top Sellers of the Category: Product/Article Pages, Category Pages
  • Example Use Case: Display the products that can complete the user flow of discovery, add to cart, and purchase. These products indicate good price-value performance and give the other users the feeling of being preferred. With price or category filters, you can increase purchase rates of unexplored categories and create upsell opportunities.
  • Fallback Algorithms: Top Sellers of Parent Category
  • Prerequisites: 30 days of product purchase data and at least 100 in-stock products
  • Maximum Number of Products to Recommend (in the same variant): 90

Highest Discounted Products

The Highest Discounted Products algorithm generates recommendations based on discount ratios during the selected lookback period in the same locale (the website's language the user visits). It recommends products in a sequence based on the extent of their discount ratios, prioritizing those with the highest discounts. Insider receives the original and discounted prices from your product catalog and calculates the discount ratio % for each product. Recommended products will be sorted from the highest discount to the lowest for the given size. For each currency type, the discount ratio is calculated separately. All users see the same recommendation.

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Pages, Product/Article Pages, Category Pages, Cart Pages
  • Example Use Case: Promote the highest-discounted products to discount seekers (high-discount affinity segment) to capture their attention more easily.
  • Fallback Algorithms: Highest Discounted Products of Parent Category
  • Prerequisites: Original Price and Price attributes, and at least 100 in-stock products
  • Maximum Number of Products to Recommend (in the same variant): 90

Manual Merchandising

The Manual Merchandising algorithm retrieves manually specified product details, ensuring that only items currently in stock are included in the recommendations. It allows displaying particular products or content specified in the campaign configuration, making it ideal for showcasing specific items, especially during special occasions or events. All users see the same recommendation.

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Pages, Product/Article Pages, Category Pages, Cart Pages
  • Use Cases: Promote specific products on the home page to quickly sell out their stock or highlight new arrivals.
  • Fallback Algorithms: NA
  • Prerequisites: NA
  • Maximum Number of Products to Recommend (in the same variant): 50

New Arrivals

The New Arrivals algorithm highlights products recently added to your website and suggests them in a sequence based on the first date they've been ingested into the catalog. It prioritizes recommendations based on the chronological order of product appearance on your website. 

  • Available Channels:Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Pages, Product/Article Pages, Category Pages, Cart Pages
  • Example Use Case: Promote new arrivals, especially new season products, to increase sales; emphasize newly arrived items based on the first visit rather than the time added to the website.
  • Fallback Algorithms: New Arrivals of Parent Category
  • Prerequisites: At least 100 in stock products
  • Maximum Number of Products to Recommend (in the same variant): 90

Trending Products

The Trending Products algorithm employs a scoring system to recommend items, focusing on this week's trending products compared to the previous week. It assigns scores based on weekly view and purchase information, allowing for a dynamic and data-driven approach to suggest trending items. 

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Pages, Product/Article Pages, Category Pages, Cart Pages
  • Example Use Case: Influence users by displaying products that receive the most attention in terms of visit/purchase metrics over time. No real personalization unless the user is interested in prominent items.
  • Fallback Algorithms: Trending Products of Parent Category
  • Prerequisites: 2 Weeks of product purchase and views, and at least 100 in stock products
  • Maximum Number of Products to Recommend (in the same variant): 90
We do not recommend using this algorithm unless you have at least 2 weeks of product purchases and views.

Most Valuable Products

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

  • Available Channels: Web Smart Recommender, App Smart Recommender, InStory, and Email
  • Page Type: All Pages, Product/Article Pages, Category Pages, Cart Pages
  • Example Use Case: Promote more revenue-generating products on your website. 
  • Fallback Algorithms: Most Valuable Of Parent Category
  • Prerequisites: At least 100 in stock products
  • Maximum Number of Products to Recommend (in the same variant): 90
To ensure accurate recommendations for products with higher revenue, it is recommended that you select a minimum look-back period of 3 days.
Related articles