Learn about our Best next predictive product recommendations.
Overview
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.
How best next recommendations work
When a best next recommendation is created, your order data is analysed. Customers and products are added to a matrix (see below). Customers' orders are added to the matrix and the model looks for patterns. Customers with similar purchase behaviour are grouped together. There are your 'similar shoppers'.
Next, the model looks for purchase differences between similar shoppers. The missing products in their matrix will be ranked and then considered for recommendation.
Accessing predictive recommendations
If your account does not have predictive recommendations enabled, go to Campaign > Product recommendations, click Create recommendation, mouse over the recommendation type you're after under the 'Predictive' section and click on Learn more.
The sidebar will allow you to request the feature is enabled on your account (for an additional monthly charge). We'll first review your data and then confirm with you that the feature is ready to use, or if there are data dependencies to be resolved first.
Predictive recommendations are available on a 14-day free trial.
Getting the best results
Before getting started, please review the data dependencies for this product recommendation type.
This model is forgiving of catalogs with low detail. It only considers order data for making recommendations. The more order data you have, the higher the accuracy of the recommendations.
Why use Best next recommendations?
Best next has lower data dependencies than used by our lookalikes recommendation (content-based filtering). As such, it is able to generate recommendations quickly. It provides good quality recommendations for most types of retailer.