Recommendations

Luigi’s Box Recommendations is a powerful system designed to increase user engagement and sales by displaying relevant products. It utilizes AI-powered models trained on product catalog data and user behavior to deliver personalized and contextually appropriate suggestions. The models are trained on a per-customer basis to meet specific business goals, such as recommending complementary accessories or alternative items.

Luigi’s Box offers several integration paths. For a fast frontend implementation, Recco.js gives you a complete widget. For full flexibility, Recommender API lets you build the UI yourself. For scheduled offline scenarios, Batch Publisher generates recommendation batches for large user sets.

Choose your integration path

Recommended for web

Recco.js

A frontend JavaScript library for recommendation widgets with built-in rendering, analytics, and storefront-friendly behavior.

• Fastest way to ship recommendation widgets.
• Supports templates and carousel-like layouts.
• Handles the common storefront flow for you.

Custom build

Recommender API

A flexible endpoint for teams that want to control rendering, request batching, and the surrounding business logic.

• Full control over the recommendation experience.
• Fits custom storefronts and backend-driven flows.
• Supports contextual filtering and batching.

Start here

Still deciding which recommender to show? Start with Choosing recommendation models.

Want the fastest storefront widget? Continue with Integrating Recco.js.

Need a custom widget or backend flow? Continue with Building custom recommendations with the Recommender API.

Core concepts

• Recommendation models: The AI component that drives recommendations. Models can be content-based (using product data) or behavioral (observing user interactions like frequently bought together).
• Personalization: By providing a user_id in the request, the model uses the user’s profile to tailor results.
• Batching: When displaying several recommenders on a single page, batch all requests into a single API call for better performance and automatic deduplication.
• Batch publishing: For offline scenarios like newsletters, generate personalized recommendation batches on a schedule.