Overview

Core Algorithms are pre-built recommendation strategies in Netcore Unbxd that help you surface relevant products using proven business logic. These algorithms power common merchandising use cases such as personalisation, cross-sell, and product discovery.

Use these algorithms as-is or combine them to create custom, hybrid recommendation strategies tailored to your business goals.

🚧
How Does it Work?
Core algorithms establish relationships between:

A shopper and products (personalization)

A product and related products (similarity or co-occurrence)

This enables you to deliver contextual and intent-driven recommendations across your storefront.

To access the core algorithms, log in to Netcore Unbxd Recommendation Console and navigate to Algorithms > Core Algorithms

Available Algorithms

Refer to the table below for the list of available algorithms and the primary use case with suggested placement across website.

Algorithm	What it does	Primary Use Case	Best Placement
Recommended For You	Recommends products based on a shopper’s browsing and product view history	Personalization	Homepage, Zero-result search page
Top Sellers	Showcases most sold products based on historical sales data	Social proof, trending products	Homepage, PDP
Bought Also Bought	Recommends products frequently purchased together	Cross-sell	PDP, Order confirmation page
Viewed Also Viewed	Suggests products commonly viewed together	Alternatives, discovery	PDP
More Like This	Displays similar products using text and category matching	Similar product discovery	PDP
Recently Viewed	Shows products viewed by the shopper in recent sessions	Session continuity	Homepage, Zero-result search page
Complete The Look	Curates complementary products for a given product	Styling, bundling	PDP
Cross-Sell	Recommends complementary products based on business logic	Increase cart value	PDP, Cart page
Category Top Sellers	Highlights best-selling products within a category	Category-level merchandising	Category pages
Brand Top Sellers	Highlights best-selling products within a brand	Brand-focused merchandising	Brand pages, PDP
AI-based Complete the Look	Uses AI to automatically generate product combinations	Automated styling recommendations	PDP
Recs based on Recently Viewed	Recommends products derived from recently viewed items	Extend session-based discovery	Homepage, PDP
Recs based on Last Viewed	Recommends products based on the most recently viewed product	Quick re-engagement	PDP, Homepage
Boutique	Displays curated or manually controlled product collections	Editorial merchandising	Homepage, Campaign pages

Use Case vs Recommended Algorithm

Refer to the table below to understand which algorithm works best for various use cases.

Use Case	Recommended Algorithm
Personalization	Recommended For You
Social proof	Top Sellers
Cross-sell	Bought Also Bought
Product alternatives	Viewed Also Viewed
Similar products	More Like This
Session continuity	Recently Viewed
Styling/bundling	Complete The Look