Choosing recommendation models

Introduction

This guide provides strategic advice on which recommendation models to use on different parts of your website. Choosing the right model for the right context is key to maximizing engagement, increasing order value, and creating a better user experience.

While the technical implementation is covered in other guides, this document focuses on the “why” and “where” of using Luigi’s Box’s powerful recommendation models.

What you’ll learn

• Which models are best suited for product pages, category pages, shopping carts, and homepages.
• How to use different models to achieve specific business goals like upselling, cross-selling, and personalization.
• A framework for thinking about your overall recommendation strategy.

Who is this guide for

• Developers who are planning their recommendation strategy.
• Users looking to understand the business value of different recommendation types.

Choosing models by page type

The most effective recommendation strategies are context-aware. A recommendation that works well on a product page might not be the best choice for the homepage. Here’s a breakdown of the best models for key pages on your site.

1. The product detail page (PDP)

Goal: Keep the user engaged with your catalog and encourage them to either upgrade their choice (upsell) or add more items to their cart (cross-sell).

• For “You might also like” (alternatives):

  • Model: item_detail_alternatives
  • Why: This model is perfect for showing similar products. It’s trained to find alternatives that are often slightly more expensive, which can help increase the average order value. It helps users find the perfect product if the current one isn’t quite right.

• For “Frequently bought together” (complements):

  • Model: item_detail_complements
  • Why: This is the classic cross-sell model. It recommends items that are commonly purchased with the product being viewed, like accessories, batteries, or matching items. This is a highly effective way to increase the number of items per order.

2. The shopping cart / basket page

Goal: Keep the user in buying mode after they add an item to their cart, and lift the final order value before checkout.

• For the add-to-cart popup (“You might also need”):

  • Model: basket_popup
  • Why: This is the highest-impact basket recommendation. The popup appears the moment a user adds an item to their cart, while they’re still in buying mode and most receptive to another suggestion. It cross-sells against the most recently added product, capturing attention before the user navigates away.

• For the basket detail page (“Complete your order”):

  • Model: basket
  • Why: This model considers every item currently in the cart and suggests products that complement the entire order. By the time a user reaches the basket detail page, they’re usually done shopping and ready to check out — so the best opportunities here are small add-ons, like an extra item to hit a free-shipping threshold.

3. The product listing page (PLP)

Goal: Help the user find what they’re looking for faster, reducing the need to scroll through the entire category.

• For “Top picks in this category”:
  • Model: category
  • Why: This model surfaces trending products from the current category, personalized to the user and diversified across subcategories. Instead of forcing the user to scroll through hundreds of items, it offers a curated shortcut to the most relevant products on the page.

4. The homepage

Goal: Capture the user’s interest immediately and guide them toward what they’re most likely to buy.

The strongest homepages stack several recommendation strips: start with category shortcuts, follow with personalized product picks, and finish with broader discovery sections like trends, discounts, or new arrivals.

• Start with a shortcut to favorite categories (“Your top categories”):

  • Model: top_categories
  • Why: This points returning users straight to the categories they’ve shown the most interest in, saving clicks before they even start browsing.

• Follow with personalized product picks (“Picked for you”):

  • Model: user_click_based, user_conversion_based, or favorites
  • Why: Choose based on your shop. user_click_based works well for most stores by recommending products similar to recently viewed but unpurchased items. user_conversion_based leans on past purchases, while favorites is ideal for consumable goods where users tend to repeat-buy.

• Finish with broad-appeal products (“Trending now”, discounts, or new arrivals):

  • Model: trends, discount, or news
  • Why: Round out the page with broadly appealing products. Use trends for popular items, discount if promotions drive your shop, or news (novelties) if your audience values being first to see new arrivals.

For brand-new visitors without any history, trends alone is a reliable fallback until you’ve collected enough data to personalize.

5. 404 and “No search results” pages

Goal: Recover a broken user journey when there’s nothing better to show.

These pages are not as critical as the others — most users who land here have already gone off-track, and you can leave them without recommendations. If you do want to use the space, keep it simple:

• Model: top_categories, followed by trends (or discount / news, depending on your shop)
• Why: Offer clear shortcuts back into the catalog — favorite categories first, then broadly popular or relevant products as a fallback.

Next steps

Now that you have a basic understanding of recommender models:

• For the recommended web integration: Continue to the Integrating Recco.js for on-site recommendations guide.
• For a custom UI or non-web integration: Continue to the Building custom recommendations with the Recommender API guide.
• To explore more models: Continue to the Reference models page.