How to Create a Related Products Recommendation Preset

Related Products presets surface complementary items — the things customers buy together with what they’re already looking at. Maestra Platform offers three variations, each tuned for a different placement. Related Products recommendations are built from customer actions with products. The target product needs at least 100 actions for the preset to produce personalized recommendations — otherwise it falls back to bestsellers. The preset counts actions with products from the segments in Recommend for products and Recommend from, over the window set in Take into account actions with products for. If none of the products in those segments have enough actions, the preset stops and a warning appears on the project. To fix it, widen the time window or switch to a different preset that fits the campaign.

​

Related Products Recommendation Preset

Surfaces complementary products and builds recommendations for a specific item. Higher-priced items get more recommendations; lower-priced items get fewer.

• Best used for “Frequently bought together” and “Customers also bought” modules.
• Works for identified and anonymous customers.
• Available through the API (recommendation widget) and email.

Good to know:

• Signals used: same-order co-occurrence, plus category and attribute co-purchase patterns. The ML model can predict recommendations even for products with no order history yet.
• Refresh: once a day.
• Limit: up to 5 instances per project.
• Segment: can be limited to a product segment.
• Auto-filters: checks the product’s area; product external systems match by default.

​

Often Purchased With Items in Product List Recommendation Preset

The Related Products preset applied to each item on a customer’s product list. The number of recommendations scales with product price — more for expensive items, fewer for cheaper ones. Recalculates in real time based on the customer’s orders.

• Best used for abandoned Cart, Favorites recommendations, and on-site Cart modules.
• Works for identified and anonymous customers.
• Available through the API (recommendation widget) and email.

Good to know:

• Refresh: real time.
• Limit: up to 3 instances per project.
• Auto-filters: checks the product’s area and brand (multi-brand projects).

​

Post-purchase Cross-sell Recommendation Preset

The Related Products preset applied to each item in the customer’s most recently updated order, with recommendation volume proportional to price. Recalculates in real time.

• Best used for “Thanks for your order” and “Next order suggestion” flows.
• Identified customers only.
• Available through the API (recommendation widget) and email.

Good to know:

• Refresh: real time.
• Limit: up to 1 instance per project.
• Auto-filters: checks the product’s area and brand (multi-brand projects).

​

How to set it up

​

Usage example

Say you want to surface related products from the “Scarves” segment for the “Coats” segment (system name Coats).

1. Create a recommendation using the Related Products Recommendation Preset:
   • Select the segments in the settings.
   • Launch it.
   • You’ll get the parameter Product.Recommendations.Soputstvuyuschieprodukti.
2. Insert the parameter into your email. Use Take() to limit the segment size so the email can render even when the segment is large. Sample markup for this example, which outputs the name of the recommended product:
   @{for prod in Products.GetBySegment("Coats").Take(5)}
              @{for item in prod.Product.Recommendations.Soputstvuyuschieprodukti.Take(2)}
                 ...${item.Name}...
              @{end for}
           @{end for}