Skip to main content
All CollectionsCommerceProduct recommendations
Hybrid prediction product recommendations
Hybrid prediction product recommendations

Combine data points from Best next and Lookalike recommendations.

Gareth Burroughes avatar
Written by Gareth Burroughes
Updated over a month ago

Our Hybrid prediction product recommendation uses historical data to determine the best product recommendation for a specific customer from two of our popular recommendation models: Lookalikes and Best next.

Best next

Best next is a predictive recommendation type. It uses a type of machine learning called collaborative filtering to find lookalike shoppers. Similar shoppers' behaviour can help find recommendations.

Lookalikes

Lookalikes is a predictive recommendation type. It uses a type of machine learning called content-based filtering to find the types of products a customer has shown an interest in.


Before you start

Things you need to know:

  • Hybrid recommendations require both order and catalog data to work.


How Hybrid prediction works

The Hybrid prediction model uses two of our machine-learning-powered recommendations, utilising the capabilities of both Lookalikes and Best Next to provide the best possible recommendations for each customer.

The model uses the best-performing method in every case by predicting and evaluating the performance of different machine-learning algorithms.

For customers with insufficient orders to generate an accurate recommendation, Hybrid prediction recommends best-selling products to ensure there's something for everyone.


Create a Hybrid prediction product recommendation

  1. Go to Content > Products > Recommendations.

  2. Select CREATE RECOMMENDATION.

    mceclip0.png

  3. Hover over the Hybrid prediction tile, and select SELECT.

  4. On the side panel, expand the Choose catalog drop-down menu, then choose the catalog you want to use.

    mceclip1.png

  5. For Recommendation name, enter a name for the recommendation.

    Make it something you can easily recognise.

  6. Select CREATE.

  7. On the Recommendation builder, choose any include or exclude rules that you want to set up.

  8. For If no recommendations are found, select [click to select fallback] and choose a fallback product recommendation for customers where no Hybrid recommendation can be found.

    mceclip2.png

  9. Select SAVE, then wait for the recommendation status to change to Ready.


Preview a Hybrid prediction product recommendation

  1. Go to Content > Products > Recommendations.

  2. Select the name of your Hybrid prediction product recommendation.

  3. Select Preview.

  4. Select the email address of the contact you want to preview recommendations for. Here you can see all the recommended products for the contact.

  5. When done, select CLOSE.

Did this answer your question?